Model save

README.md

@@ -0,0 +1,75 @@
+---
+base_model: sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat
+
+This model is a fine-tuned version of [sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat](https://huggingface.co/sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6412
+- Rewards/chosen: -0.1044
+- Rewards/rejected: -0.2494
+- Rewards/accuracies: 0.6445
+- Rewards/margins: 0.1450
+- Logps/rejected: -429.4582
+- Logps/chosen: -433.6304
+- Logits/rejected: -3.2047
+- Logits/chosen: -3.2544
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6795        | 0.2092 | 100  | 0.6759          | 0.0017         | -0.0328          | 0.6289             | 0.0345          | -407.8037      | -423.0197    | -3.2565         | -3.3136       |
+| 0.6584        | 0.4184 | 200  | 0.6534          | -0.0666        | -0.1617          | 0.6445             | 0.0951          | -420.6952      | -429.8561    | -3.2240         | -3.2768       |
+| 0.6494        | 0.6276 | 300  | 0.6438          | -0.1077        | -0.2410          | 0.6211             | 0.1333          | -428.6237      | -433.9640    | -3.2050         | -3.2553       |
+| 0.6428        | 0.8368 | 400  | 0.6415          | -0.1001        | -0.2437          | 0.6211             | 0.1436          | -428.8884      | -433.2000    | -3.2046         | -3.2543       |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.2+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -3.25435733795166,
+    "eval_logits/rejected": -3.204742431640625,
+    "eval_logps/chosen": -433.63043212890625,
+    "eval_logps/rejected": -429.45819091796875,
+    "eval_loss": 0.6412035226821899,
+    "eval_rewards/accuracies": 0.64453125,
+    "eval_rewards/chosen": -0.10438449680805206,
+    "eval_rewards/margins": 0.14497718214988708,
+    "eval_rewards/rejected": -0.24936166405677795,
+    "eval_runtime": 8.2917,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 241.204,
+    "eval_steps_per_second": 3.859,
+    "total_flos": 0.0,
+    "train_loss": 0.6571792745689967,
+    "train_runtime": 784.6622,
+    "train_samples": 61135,
+    "train_samples_per_second": 77.913,
+    "train_steps_per_second": 0.609
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -3.25435733795166,
+    "eval_logits/rejected": -3.204742431640625,
+    "eval_logps/chosen": -433.63043212890625,
+    "eval_logps/rejected": -429.45819091796875,
+    "eval_loss": 0.6412035226821899,
+    "eval_rewards/accuracies": 0.64453125,
+    "eval_rewards/chosen": -0.10438449680805206,
+    "eval_rewards/margins": 0.14497718214988708,
+    "eval_rewards/rejected": -0.24936166405677795,
+    "eval_runtime": 8.2917,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 241.204,
+    "eval_steps_per_second": 3.859
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1c7b079c6fe16b8306f4ad14c51991d2f4687c5913f4c69aaca2a0348cc737
+size 4987196936

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9629c04e2da5a942f500f775442430cc7cbc755c6e95af6b26a3c7de9af646e9
+size 1296089984

model.safetensors.index.json

@@ -0,0 +1,64 @@
+{
+  "metadata": {
+    "total_size": 6283280384
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

runs/Apr26_15-48-43_ip-26-0-160-225/events.out.tfevents.1714147034.ip-26-0-160-225.711598.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1fc27bf5185d63cd4e2dfcd363e9724966b1098397dd6e5f8a59a1a161d08c
-size 19346
+oid sha256:2f5835ae8637ba91ca29d3afbfe85b2fdbacaa6b26c7ca7683878a0ac5a110e8
+size 21764

runs/Apr26_15-48-43_ip-26-0-160-225/events.out.tfevents.1714147827.ip-26-0-160-225.711598.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b158da38885dfc714a392467a3ae1215e3432959ad5762c3ae7cf3464549eeac
+size 828

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.6571792745689967,
+    "train_runtime": 784.6622,
+    "train_samples": 61135,
+    "train_samples_per_second": 77.913,
+    "train_steps_per_second": 0.609
+}

trainer_state.json

@@ -0,0 +1,394 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 478,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0020920502092050207,
+      "grad_norm": 9.710838317871094,
+      "learning_rate": 1.0416666666666666e-08,
+      "logits/chosen": -3.161454916000366,
+      "logits/rejected": -3.0680501461029053,
+      "logps/chosen": -437.20782470703125,
+      "logps/rejected": -343.8380432128906,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.05230125523012552,
+      "grad_norm": 8.52570629119873,
+      "learning_rate": 2.604166666666667e-07,
+      "logits/chosen": -3.30265212059021,
+      "logits/rejected": -3.2195777893066406,
+      "logps/chosen": -432.7400207519531,
+      "logps/rejected": -391.2707824707031,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": 0.0006945470231585205,
+      "rewards/margins": 0.0007254942320287228,
+      "rewards/rejected": -3.094731437158771e-05,
+      "step": 25
+    },
+    {
+      "epoch": 0.10460251046025104,
+      "grad_norm": 9.973247528076172,
+      "learning_rate": 4.999733114418725e-07,
+      "logits/chosen": -3.299149751663208,
+      "logits/rejected": -3.2438504695892334,
+      "logps/chosen": -446.8968811035156,
+      "logps/rejected": -404.587158203125,
+      "loss": 0.6914,
+      "rewards/accuracies": 0.5799999833106995,
+      "rewards/chosen": 0.005268932785838842,
+      "rewards/margins": 0.002896952675655484,
+      "rewards/rejected": 0.002371980343014002,
+      "step": 50
+    },
+    {
+      "epoch": 0.15690376569037656,
+      "grad_norm": 9.357086181640625,
+      "learning_rate": 4.951516761176343e-07,
+      "logits/chosen": -3.302896738052368,
+      "logits/rejected": -3.225714683532715,
+      "logps/chosen": -480.6836853027344,
+      "logps/rejected": -436.4853515625,
+      "loss": 0.6871,
+      "rewards/accuracies": 0.5975000262260437,
+      "rewards/chosen": 0.013074235059320927,
+      "rewards/margins": 0.012715624645352364,
+      "rewards/rejected": 0.0003586093371268362,
+      "step": 75
+    },
+    {
+      "epoch": 0.20920502092050208,
+      "grad_norm": 8.75236988067627,
+      "learning_rate": 4.821741763807186e-07,
+      "logits/chosen": -3.2598507404327393,
+      "logits/rejected": -3.2092175483703613,
+      "logps/chosen": -426.1629638671875,
+      "logps/rejected": -389.50421142578125,
+      "loss": 0.6795,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": 0.003723819274455309,
+      "rewards/margins": 0.02804265171289444,
+      "rewards/rejected": -0.02431883104145527,
+      "step": 100
+    },
+    {
+      "epoch": 0.20920502092050208,
+      "eval_logits/chosen": -3.313567638397217,
+      "eval_logits/rejected": -3.2565112113952637,
+      "eval_logps/chosen": -423.0196533203125,
+      "eval_logps/rejected": -407.8036804199219,
+      "eval_loss": 0.6759119629859924,
+      "eval_rewards/accuracies": 0.62890625,
+      "eval_rewards/chosen": 0.0017230990342795849,
+      "eval_rewards/margins": 0.0345395989716053,
+      "eval_rewards/rejected": -0.03281649947166443,
+      "eval_runtime": 8.2733,
+      "eval_samples_per_second": 241.742,
+      "eval_steps_per_second": 3.868,
+      "step": 100
+    },
+    {
+      "epoch": 0.2615062761506276,
+      "grad_norm": 8.889654159545898,
+      "learning_rate": 4.614725560802639e-07,
+      "logits/chosen": -3.2867064476013184,
+      "logits/rejected": -3.2023117542266846,
+      "logps/chosen": -430.924560546875,
+      "logps/rejected": -382.1640319824219,
+      "loss": 0.6731,
+      "rewards/accuracies": 0.6474999785423279,
+      "rewards/chosen": -0.01004675030708313,
+      "rewards/margins": 0.04363078624010086,
+      "rewards/rejected": -0.05367753654718399,
+      "step": 125
+    },
+    {
+      "epoch": 0.3138075313807531,
+      "grad_norm": 9.882610321044922,
+      "learning_rate": 4.337355301007335e-07,
+      "logits/chosen": -3.222916841506958,
+      "logits/rejected": -3.1899585723876953,
+      "logps/chosen": -443.3583679199219,
+      "logps/rejected": -414.344970703125,
+      "loss": 0.667,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.017106110230088234,
+      "rewards/margins": 0.06052257865667343,
+      "rewards/rejected": -0.07762870192527771,
+      "step": 150
+    },
+    {
+      "epoch": 0.36610878661087864,
+      "grad_norm": 9.968969345092773,
+      "learning_rate": 3.9988587174999306e-07,
+      "logits/chosen": -3.2201168537139893,
+      "logits/rejected": -3.131910800933838,
+      "logps/chosen": -477.7035217285156,
+      "logps/rejected": -405.7104797363281,
+      "loss": 0.6574,
+      "rewards/accuracies": 0.6399999856948853,
+      "rewards/chosen": -0.03587143123149872,
+      "rewards/margins": 0.09045815467834473,
+      "rewards/rejected": -0.12632958590984344,
+      "step": 175
+    },
+    {
+      "epoch": 0.41841004184100417,
+      "grad_norm": 9.230700492858887,
+      "learning_rate": 3.610497133404795e-07,
+      "logits/chosen": -3.23995304107666,
+      "logits/rejected": -3.1550867557525635,
+      "logps/chosen": -431.6617126464844,
+      "logps/rejected": -396.62774658203125,
+      "loss": 0.6584,
+      "rewards/accuracies": 0.6349999904632568,
+      "rewards/chosen": -0.06991340965032578,
+      "rewards/margins": 0.08443903923034668,
+      "rewards/rejected": -0.15435244143009186,
+      "step": 200
+    },
+    {
+      "epoch": 0.41841004184100417,
+      "eval_logits/chosen": -3.2767982482910156,
+      "eval_logits/rejected": -3.2240023612976074,
+      "eval_logps/chosen": -429.85614013671875,
+      "eval_logps/rejected": -420.6952209472656,
+      "eval_loss": 0.6533502340316772,
+      "eval_rewards/accuracies": 0.64453125,
+      "eval_rewards/chosen": -0.06664139777421951,
+      "eval_rewards/margins": 0.09509073942899704,
+      "eval_rewards/rejected": -0.16173213720321655,
+      "eval_runtime": 8.2763,
+      "eval_samples_per_second": 241.653,
+      "eval_steps_per_second": 3.866,
+      "step": 200
+    },
+    {
+      "epoch": 0.4707112970711297,
+      "grad_norm": 10.79430103302002,
+      "learning_rate": 3.185190812915646e-07,
+      "logits/chosen": -3.1671783924102783,
+      "logits/rejected": -3.118861436843872,
+      "logps/chosen": -446.6968994140625,
+      "logps/rejected": -410.1864013671875,
+      "loss": 0.6518,
+      "rewards/accuracies": 0.6449999809265137,
+      "rewards/chosen": -0.08074235171079636,
+      "rewards/margins": 0.10100732743740082,
+      "rewards/rejected": -0.18174967169761658,
+      "step": 225
+    },
+    {
+      "epoch": 0.5230125523012552,
+      "grad_norm": 10.086767196655273,
+      "learning_rate": 2.7370891215954565e-07,
+      "logits/chosen": -3.1980080604553223,
+      "logits/rejected": -3.1623446941375732,
+      "logps/chosen": -440.4261474609375,
+      "logps/rejected": -439.9627685546875,
+      "loss": 0.6476,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -0.07635506987571716,
+      "rewards/margins": 0.11709018051624298,
+      "rewards/rejected": -0.19344525039196014,
+      "step": 250
+    },
+    {
+      "epoch": 0.5753138075313807,
+      "grad_norm": 9.709197044372559,
+      "learning_rate": 2.2810997961375938e-07,
+      "logits/chosen": -3.216128349304199,
+      "logits/rejected": -3.1448960304260254,
+      "logps/chosen": -425.5062561035156,
+      "logps/rejected": -391.5084228515625,
+      "loss": 0.6461,
+      "rewards/accuracies": 0.6800000071525574,
+      "rewards/chosen": -0.072402223944664,
+      "rewards/margins": 0.1306913197040558,
+      "rewards/rejected": -0.2030935436487198,
+      "step": 275
+    },
+    {
+      "epoch": 0.6276150627615062,
+      "grad_norm": 10.980072975158691,
+      "learning_rate": 1.8323929841460178e-07,
+      "logits/chosen": -3.2006824016571045,
+      "logits/rejected": -3.1383109092712402,
+      "logps/chosen": -443.0799865722656,
+      "logps/rejected": -436.2774658203125,
+      "loss": 0.6494,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.1245601624250412,
+      "rewards/margins": 0.10581608861684799,
+      "rewards/rejected": -0.2303762584924698,
+      "step": 300
+    },
+    {
+      "epoch": 0.6276150627615062,
+      "eval_logits/chosen": -3.2553329467773438,
+      "eval_logits/rejected": -3.2049574851989746,
+      "eval_logps/chosen": -433.9639892578125,
+      "eval_logps/rejected": -428.6236572265625,
+      "eval_loss": 0.6438009142875671,
+      "eval_rewards/accuracies": 0.62109375,
+      "eval_rewards/chosen": -0.10771973431110382,
+      "eval_rewards/margins": 0.13329659402370453,
+      "eval_rewards/rejected": -0.24101632833480835,
+      "eval_runtime": 8.3559,
+      "eval_samples_per_second": 239.351,
+      "eval_steps_per_second": 3.83,
+      "step": 300
+    },
+    {
+      "epoch": 0.6799163179916318,
+      "grad_norm": 9.95361614227295,
+      "learning_rate": 1.4058965538597032e-07,
+      "logits/chosen": -3.2326276302337646,
+      "logits/rejected": -3.198971748352051,
+      "logps/chosen": -443.37371826171875,
+      "logps/rejected": -433.8561706542969,
+      "loss": 0.6392,
+      "rewards/accuracies": 0.6399999856948853,
+      "rewards/chosen": -0.11981040984392166,
+      "rewards/margins": 0.12150833755731583,
+      "rewards/rejected": -0.2413187474012375,
+      "step": 325
+    },
+    {
+      "epoch": 0.7322175732217573,
+      "grad_norm": 10.580938339233398,
+      "learning_rate": 1.0157994641835734e-07,
+      "logits/chosen": -3.1840951442718506,
+      "logits/rejected": -3.0981223583221436,
+      "logps/chosen": -430.7939453125,
+      "logps/rejected": -403.5060119628906,
+      "loss": 0.6447,
+      "rewards/accuracies": 0.6225000023841858,
+      "rewards/chosen": -0.15974169969558716,
+      "rewards/margins": 0.09658970683813095,
+      "rewards/rejected": -0.2563314139842987,
+      "step": 350
+    },
+    {
+      "epoch": 0.7845188284518828,
+      "grad_norm": 8.326279640197754,
+      "learning_rate": 6.75079717232744e-08,
+      "logits/chosen": -3.2011187076568604,
+      "logits/rejected": -3.0969460010528564,
+      "logps/chosen": -465.22344970703125,
+      "logps/rejected": -392.5793762207031,
+      "loss": 0.6411,
+      "rewards/accuracies": 0.6549999713897705,
+      "rewards/chosen": -0.11683624982833862,
+      "rewards/margins": 0.14286838471889496,
+      "rewards/rejected": -0.2597046196460724,
+      "step": 375
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "grad_norm": 8.851872444152832,
+      "learning_rate": 3.9507259776993954e-08,
+      "logits/chosen": -3.221069097518921,
+      "logits/rejected": -3.1744155883789062,
+      "logps/chosen": -449.8016052246094,
+      "logps/rejected": -409.0178527832031,
+      "loss": 0.6428,
+      "rewards/accuracies": 0.6524999737739563,
+      "rewards/chosen": -0.08884063363075256,
+      "rewards/margins": 0.13940051198005676,
+      "rewards/rejected": -0.22824116051197052,
+      "step": 400
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "eval_logits/chosen": -3.254263401031494,
+      "eval_logits/rejected": -3.204622507095337,
+      "eval_logps/chosen": -433.20001220703125,
+      "eval_logps/rejected": -428.88836669921875,
+      "eval_loss": 0.6415477395057678,
+      "eval_rewards/accuracies": 0.62109375,
+      "eval_rewards/chosen": -0.10007989406585693,
+      "eval_rewards/margins": 0.14358317852020264,
+      "eval_rewards/rejected": -0.24366310238838196,
+      "eval_runtime": 8.7287,
+      "eval_samples_per_second": 229.13,
+      "eval_steps_per_second": 3.666,
+      "step": 400
+    },
+    {
+      "epoch": 0.8891213389121339,
+      "grad_norm": 10.138018608093262,
+      "learning_rate": 1.850935636255496e-08,
+      "logits/chosen": -3.1941397190093994,
+      "logits/rejected": -3.1335413455963135,
+      "logps/chosen": -463.3765869140625,
+      "logps/rejected": -418.0171203613281,
+      "loss": 0.6393,
+      "rewards/accuracies": 0.6399999856948853,
+      "rewards/chosen": -0.11999661475419998,
+      "rewards/margins": 0.13007262349128723,
+      "rewards/rejected": -0.2500692307949066,
+      "step": 425
+    },
+    {
+      "epoch": 0.9414225941422594,
+      "grad_norm": 9.687002182006836,
+      "learning_rate": 5.212833302556258e-09,
+      "logits/chosen": -3.202920913696289,
+      "logits/rejected": -3.14504337310791,
+      "logps/chosen": -442.259765625,
+      "logps/rejected": -406.7275085449219,
+      "loss": 0.6419,
+      "rewards/accuracies": 0.6050000190734863,
+      "rewards/chosen": -0.13094988465309143,
+      "rewards/margins": 0.1017264574766159,
+      "rewards/rejected": -0.23267632722854614,
+      "step": 450
+    },
+    {
+      "epoch": 0.9937238493723849,
+      "grad_norm": 8.862220764160156,
+      "learning_rate": 6.004792024680294e-11,
+      "logits/chosen": -3.1527392864227295,
+      "logits/rejected": -3.1062843799591064,
+      "logps/chosen": -445.8639831542969,
+      "logps/rejected": -418.4268493652344,
+      "loss": 0.6377,
+      "rewards/accuracies": 0.6575000286102295,
+      "rewards/chosen": -0.11145105212926865,
+      "rewards/margins": 0.15232053399085999,
+      "rewards/rejected": -0.26377159357070923,
+      "step": 475
+    },
+    {
+      "epoch": 1.0,
+      "step": 478,
+      "total_flos": 0.0,
+      "train_loss": 0.6571792745689967,
+      "train_runtime": 784.6622,
+      "train_samples_per_second": 77.913,
+      "train_steps_per_second": 0.609
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 478,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

wandb/debug-internal.log

@@ -747,3 +747,208 @@
 2024-04-26 16:08:23,064 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
 2024-04-26 16:08:24,187 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
 2024-04-26 16:08:29,188 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:33,026 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:34,871 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:37,030 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:37,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:08:37,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:08:37,058 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:08:39,032 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:39,996 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:41,034 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:43,038 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:45,040 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:45,420 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:46,337 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:08:47,042 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:49,044 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:50,801 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:51,045 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:52,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:08:52,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:08:52,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:08:53,051 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:55,053 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:56,161 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:57,055 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:59,057 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:01,059 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:01,568 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:03,060 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:05,062 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:06,912 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:07,057 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:09:07,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:09:07,058 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:09:07,064 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:07,332 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-26 16:09:07,334 DEBUG   SenderThread:713738 [sender.py:send():379] send: history
+2024-04-26 16:09:07,334 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:09:07,335 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:09:08,066 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/wandb-summary.json
+2024-04-26 16:09:09,067 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:11,069 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:12,304 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:13,071 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:15,073 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:16,339 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:09:17,076 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:17,760 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:19,077 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:21,079 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:22,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:09:22,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:09:22,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:09:23,081 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:23,203 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:25,083 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:27,085 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:28,623 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:29,087 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:31,089 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:33,091 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:34,019 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:35,093 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:37,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:09:37,059 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:09:37,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:09:37,095 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:39,097 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:39,390 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:41,099 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:41,173 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-26 16:09:41,175 DEBUG   SenderThread:713738 [sender.py:send():379] send: history
+2024-04-26 16:09:41,176 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:09:41,177 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:09:42,101 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/wandb-summary.json
+2024-04-26 16:09:43,102 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:44,810 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:45,104 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:46,340 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:09:47,106 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:49,109 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:50,192 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:51,111 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:52,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:09:52,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:09:52,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:09:53,112 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:55,115 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:55,629 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:57,117 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:59,119 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:01,005 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:01,121 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:03,123 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:05,125 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:06,489 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:07,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:10:07,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:10:07,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:10:07,127 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:09,129 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:11,132 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:11,931 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:13,134 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:15,038 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-26 16:10:15,039 DEBUG   SenderThread:713738 [sender.py:send():379] send: history
+2024-04-26 16:10:15,040 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:15,041 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:15,136 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:15,137 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/wandb-summary.json
+2024-04-26 16:10:16,342 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:10:17,138 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:17,356 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:19,091 DEBUG   SenderThread:713738 [sender.py:send():379] send: telemetry
+2024-04-26 16:10:19,093 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,094 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-26 16:10:19,097 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,098 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,099 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,099 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,101 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,101 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,102 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,103 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,104 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,105 DEBUG   SenderThread:713738 [sender.py:send():379] send: history
+2024-04-26 16:10:19,105 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,106 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,141 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:19,141 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/wandb-summary.json
+2024-04-26 16:10:21,143 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:22,059 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:10:22,059 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:10:22,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:10:22,467 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:23,145 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:25,147 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:27,149 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:27,423 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-26 16:10:27,425 DEBUG   SenderThread:713738 [sender.py:send():379] send: history
+2024-04-26 16:10:27,425 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:27,429 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:28,151 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/wandb-summary.json
+2024-04-26 16:10:28,437 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:29,153 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:29,154 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/config.yaml
+2024-04-26 16:10:33,569 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:10:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:10:37,122 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:10:39,164 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:39,263 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:44,264 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:46,345 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:10:49,174 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:50,203 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:52,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:10:52,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:10:52,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:10:55,181 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:55,370 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:57,183 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:59,185 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:00,468 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:01,187 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:03,189 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:05,191 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:05,523 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:07,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:11:07,120 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:11:07,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:11:07,194 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:09,196 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:10,641 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:13,200 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:15,202 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:15,699 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:16,347 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:11:17,204 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:19,207 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:21,307 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:22,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:11:22,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:11:22,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:11:27,229 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:32,323 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:11:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:11:37,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:11:37,584 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:42,686 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:46,350 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:11:47,930 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:52,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:11:52,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:11:52,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:11:53,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:58,201 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:03,288 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:07,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:12:07,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:12:07,122 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:12:08,297 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:13,359 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:16,352 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:12:18,516 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report

wandb/run-20240426_155715-vljs8xzo/files/config.yaml

@@ -32,6 +32,7 @@ _wandb:
       3:
       - 7
       - 23
+      - 62
       4: 3.11.9
       5: 0.16.6
       6: 4.40.1

wandb/run-20240426_155715-vljs8xzo/files/output.log

@@ -326,3 +326,127 @@
 {'eval_loss': 0.6415477395057678, 'eval_runtime': 8.7287, 'eval_samples_per_second': 229.13, 'eval_steps_per_second': 3.666, 'eval_rewards/chosen': -0.10007989406585693, 'eval_rewards/rejected': -0.24366310238838196, 'eval_rewards/accuracies': 0.62109375, 'eval_rewards/margins': 0.14358317852020264, 'eval_logps/rejected': -428.88836669921875, 'eval_logps/chosen': -433.20001220703125, 'eval_logits/rejected': -3.204622507095337, 'eval_logits/chosen': -3.254263401031494, 'epoch': 0.84}
 [INFO|modeling_utils.py:2598] 2024-04-26 16:08:13,074 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 2 checkpoint shards. You can find where each parameters has been saved in the index located at ./checkpoint-400/model.safetensors.index.json.
 [INFO|tokenization_utils_base.py:2488] 2024-04-26 16:08:13,077 >> tokenizer config file saved in ./checkpoint-400/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-26 16:08:13,079 >> Special tokens file saved in ./checkpoint-400/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2488] 2024-04-26 16:08:31,839 >> tokenizer config file saved in ./tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-26 16:08:31,841 >> Special tokens file saved in ./special_tokens_map.json
+[INFO|trainer.py:3397] 2024-04-26 16:08:31,870 >> Deleting older checkpoint [checkpoint-300] due to args.save_total_limit
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 89%|████████▉ | 425/478 [11:46<01:11,  1.35s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▍| 450/478 [12:20<00:37,  1.35s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 99%|█████████▉| 475/478 [12:54<00:04,  1.35s/it]
+
+100%|██████████| 478/478 [12:58<00:00,  1.35s/it][INFO|trainer.py:2316] 2024-04-26 16:10:19,036 >>
+Training completed. Do not forget to share your model on huggingface.co/models =)
+100%|██████████| 478/478 [12:58<00:00,  1.63s/it]
+[INFO|trainer.py:3614] 2024-04-26 16:10:19,102 >> ***** Running Evaluation *****
+[INFO|trainer.py:3616] 2024-04-26 16:10:19,102 >>   Num examples = 2000
+[INFO|trainer.py:3619] 2024-04-26 16:10:19,102 >>   Batch size = 8
+ 12%|█▎        | 4/32 [00:00<00:05,  5.08it/s]
+{'train_runtime': 784.6622, 'train_samples_per_second': 77.913, 'train_steps_per_second': 0.609, 'train_loss': 0.6571792745689967, 'epoch': 1.0}
+***** train metrics *****
+  epoch                    =        1.0
+  total_flos               =        0GF
+  train_loss               =     0.6572
+  train_runtime            = 0:13:04.66
+  train_samples            =      61135
+  train_samples_per_second =     77.913
+  train_steps_per_second   =      0.609
+2024-04-26 16:10:19 - INFO - __main__ - *** Training complete ***
+
+
+
+100%|██████████| 32/32 [00:08<00:00,  3.97it/s]
+[INFO|trainer.py:3305] 2024-04-26 16:10:27,430 >> Saving model checkpoint to ./
+[INFO|configuration_utils.py:471] 2024-04-26 16:10:27,432 >> Configuration saved in ./config.json
+[INFO|configuration_utils.py:697] 2024-04-26 16:10:27,434 >> Configuration saved in ./generation_config.json
+***** eval metrics *****
+  epoch                   =        1.0
+  eval_logits/chosen      =    -3.2544
+  eval_logits/rejected    =    -3.2047
+  eval_logps/chosen       =  -433.6304
+  eval_logps/rejected     =  -429.4582
+  eval_loss               =     0.6412
+  eval_rewards/accuracies =     0.6445
+  eval_rewards/chosen     =    -0.1044
+  eval_rewards/margins    =      0.145
+  eval_rewards/rejected   =    -0.2494
+  eval_runtime            = 0:00:08.29
+  eval_samples            =       2000
+  eval_samples_per_second =    241.204
+  eval_steps_per_second   =      3.859
+2024-04-26 16:10:27 - INFO - __main__ - *** Save model ***
+[INFO|modeling_utils.py:2598] 2024-04-26 16:10:37,122 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 2 checkpoint shards. You can find where each parameters has been saved in the index located at ./model.safetensors.index.json.
+[INFO|tokenization_utils_base.py:2488] 2024-04-26 16:10:37,133 >> tokenizer config file saved in ./tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-26 16:10:37,135 >> Special tokens file saved in ./special_tokens_map.json
+[INFO|trainer.py:3305] 2024-04-26 16:10:37,190 >> Saving model checkpoint to ./
+[INFO|configuration_utils.py:471] 2024-04-26 16:10:37,192 >> Configuration saved in ./config.json
+[INFO|configuration_utils.py:697] 2024-04-26 16:10:37,194 >> Configuration saved in ./generation_config.json
+[INFO|modeling_utils.py:2598] 2024-04-26 16:10:48,100 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 2 checkpoint shards. You can find where each parameters has been saved in the index located at ./model.safetensors.index.json.
+[INFO|tokenization_utils_base.py:2488] 2024-04-26 16:10:48,103 >> tokenizer config file saved in ./tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-26 16:10:48,105 >> Special tokens file saved in ./special_tokens_map.json
+[INFO|modelcard.py:450] 2024-04-26 16:10:48,202 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+events.out.tfevents.1714147827.ip-26-0-160-225.711598.1: 100%|██████████| 828/828 [00:00<00:00, 5.29kB/s]
+events.out.tfevents.1714147034.ip-26-0-160-225.711598.0: 100%|██████████| 21.8k/21.8k [00:00<00:00, 108kB/s]
+model-00001-of-00002.safetensors:   1%|          | 32.0M/4.99G [00:00<02:33, 32.3MB/s]
+events.out.tfevents.1714147034.ip-26-0-160-225.711598.0:   0%|          | 0.00/21.8k [00:00<?, ?B/s]
+
+
+
+
+
+
+
+
+
+
+

wandb/run-20240426_155715-vljs8xzo/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 0.6428, "train/grad_norm": 8.851872444152832, "train/learning_rate": 3.9507259776993954e-08, "train/rewards/chosen": -0.08884063363075256, "train/rewards/rejected": -0.22824116051197052, "train/rewards/accuracies": 0.6524999737739563, "train/rewards/margins": 0.13940051198005676, "train/logps/rejected": -409.0178527832031, "train/logps/chosen": -449.8016052246094, "train/logits/rejected": -3.1744155883789062, "train/logits/chosen": -3.221069097518921, "train/epoch": 0.8368200836820083, "train/global_step": 400, "_timestamp": 1714147683.4777088, "_runtime": 647.7768397331238, "_step": 20, "eval/loss": 0.6415477395057678, "eval/runtime": 8.7287, "eval/samples_per_second": 229.13, "eval/steps_per_second": 3.666, "eval/rewards/chosen": -0.10007989406585693, "eval/rewards/rejected": -0.24366310238838196, "eval/rewards/accuracies": 0.62109375, "eval/rewards/margins": 0.14358317852020264, "eval/logps/rejected": -428.88836669921875, "eval/logps/chosen": -433.20001220703125, "eval/logits/rejected": -3.204622507095337, "eval/logits/chosen": -3.254263401031494}
+{"train/loss": 0.6377, "train/grad_norm": 8.862220764160156, "train/learning_rate": 6.004792024680294e-11, "train/rewards/chosen": -0.11145105212926865, "train/rewards/rejected": -0.26377159357070923, "train/rewards/accuracies": 0.6575000286102295, "train/rewards/margins": 0.15232053399085999, "train/logps/rejected": -418.4268493652344, "train/logps/chosen": -445.8639831542969, "train/logits/rejected": -3.1062843799591064, "train/logits/chosen": -3.1527392864227295, "train/epoch": 1.0, "train/global_step": 478, "_timestamp": 1714147827.4227393, "_runtime": 791.7218701839447, "_step": 25, "eval/loss": 0.6412035226821899, "eval/runtime": 8.2917, "eval/samples_per_second": 241.204, "eval/steps_per_second": 3.859, "eval/rewards/chosen": -0.10438449680805206, "eval/rewards/rejected": -0.24936166405677795, "eval/rewards/accuracies": 0.64453125, "eval/rewards/margins": 0.14497718214988708, "eval/logps/rejected": -429.45819091796875, "eval/logps/chosen": -433.63043212890625, "eval/logits/rejected": -3.204742431640625, "eval/logits/chosen": -3.25435733795166, "train_runtime": 784.6622, "train_samples_per_second": 77.913, "train_steps_per_second": 0.609, "total_flos": 0.0, "train_loss": 0.6571792745689967}

wandb/run-20240426_155715-vljs8xzo/logs/debug-internal.log

@@ -747,3 +747,208 @@
 2024-04-26 16:08:23,064 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
 2024-04-26 16:08:24,187 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
 2024-04-26 16:08:29,188 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:33,026 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:34,871 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:37,030 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:37,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:08:37,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:08:37,058 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:08:39,032 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:39,996 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:41,034 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:43,038 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:45,040 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:45,420 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:46,337 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:08:47,042 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:49,044 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:50,801 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:51,045 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:52,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:08:52,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:08:52,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:08:53,051 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:55,053 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:56,161 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:08:57,055 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:08:59,057 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:01,059 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:01,568 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:03,060 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:05,062 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:06,912 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:07,057 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:09:07,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:09:07,058 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:09:07,064 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:07,332 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-26 16:09:07,334 DEBUG   SenderThread:713738 [sender.py:send():379] send: history
+2024-04-26 16:09:07,334 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:09:07,335 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:09:08,066 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/wandb-summary.json
+2024-04-26 16:09:09,067 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:11,069 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:12,304 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:13,071 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:15,073 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:16,339 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:09:17,076 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:17,760 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:19,077 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:21,079 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:22,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:09:22,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:09:22,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:09:23,081 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:23,203 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:25,083 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:27,085 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:28,623 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:29,087 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:31,089 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:33,091 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:34,019 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:35,093 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:37,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:09:37,059 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:09:37,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:09:37,095 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:39,097 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:39,390 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:41,099 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:41,173 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-26 16:09:41,175 DEBUG   SenderThread:713738 [sender.py:send():379] send: history
+2024-04-26 16:09:41,176 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:09:41,177 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:09:42,101 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/wandb-summary.json
+2024-04-26 16:09:43,102 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:44,810 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:45,104 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:46,340 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:09:47,106 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:49,109 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:50,192 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:51,111 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:52,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:09:52,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:09:52,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:09:53,112 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:55,115 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:55,629 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:09:57,117 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:09:59,119 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:01,005 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:01,121 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:03,123 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:05,125 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:06,489 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:07,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:10:07,058 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:10:07,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:10:07,127 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:09,129 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:11,132 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:11,931 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:13,134 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:15,038 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-26 16:10:15,039 DEBUG   SenderThread:713738 [sender.py:send():379] send: history
+2024-04-26 16:10:15,040 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:15,041 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:15,136 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:15,137 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/wandb-summary.json
+2024-04-26 16:10:16,342 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:10:17,138 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:17,356 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:19,091 DEBUG   SenderThread:713738 [sender.py:send():379] send: telemetry
+2024-04-26 16:10:19,093 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,094 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-26 16:10:19,097 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,098 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,099 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,099 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,101 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,101 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,102 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,103 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,104 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,105 DEBUG   SenderThread:713738 [sender.py:send():379] send: history
+2024-04-26 16:10:19,105 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:19,106 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:19,141 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:19,141 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/wandb-summary.json
+2024-04-26 16:10:21,143 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:22,059 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:10:22,059 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:10:22,059 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:10:22,467 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:23,145 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:25,147 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:27,149 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:27,423 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-26 16:10:27,425 DEBUG   SenderThread:713738 [sender.py:send():379] send: history
+2024-04-26 16:10:27,425 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: summary_record
+2024-04-26 16:10:27,429 INFO    SenderThread:713738 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-26 16:10:28,151 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/wandb-summary.json
+2024-04-26 16:10:28,437 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:29,153 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:29,154 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/config.yaml
+2024-04-26 16:10:33,569 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:10:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:10:37,122 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:10:39,164 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:39,263 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:44,264 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:46,345 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:10:49,174 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:50,203 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:52,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:10:52,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:10:52,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:10:55,181 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:55,370 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:10:57,183 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:10:59,185 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:00,468 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:01,187 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:03,189 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:05,191 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:05,523 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:07,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:11:07,120 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:11:07,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:11:07,194 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:09,196 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:10,641 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:13,200 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:15,202 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:15,699 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:16,347 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:11:17,204 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:19,207 INFO    Thread-12 :713738 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-dpo-ultrafeedback/wandb/run-20240426_155715-vljs8xzo/files/output.log
+2024-04-26 16:11:21,307 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:22,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:11:22,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:11:22,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:11:27,229 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:32,323 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:11:37,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:11:37,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:11:37,584 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:42,686 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:46,350 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:11:47,930 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:52,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:11:52,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:11:52,121 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:11:53,120 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:11:58,201 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:03,288 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:07,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-26 16:12:07,121 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-26 16:12:07,122 DEBUG   SenderThread:713738 [sender.py:send_request():406] send_request: stop_status
+2024-04-26 16:12:08,297 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:13,359 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report
+2024-04-26 16:12:16,352 DEBUG   SenderThread:713738 [sender.py:send():379] send: stats
+2024-04-26 16:12:18,516 DEBUG   HandlerThread:713738 [handler.py:handle_request():146] handle_request: status_report