Model save
Browse files- README.md +1 -2
- all_results.json +10 -10
- config.json +1 -1
- eval_results.json +5 -5
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- tokenizer.json +2 -2
- train_results.json +6 -6
- trainer_state.json +547 -65
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -4,7 +4,6 @@ library_name: transformers
|
|
| 4 |
model_name: llama_check_tuned
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- alignment-handbook
|
| 8 |
- trl
|
| 9 |
- sft
|
| 10 |
licence: license
|
|
@@ -28,7 +27,7 @@ print(output["generated_text"])
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
| 31 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/vedaantj/ft-llm/runs/
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
| 34 |
|
|
|
|
| 4 |
model_name: llama_check_tuned
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- trl
|
| 8 |
- sft
|
| 9 |
licence: license
|
|
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/vedaantj/ft-llm/runs/pq3g1op3)
|
| 31 |
|
| 32 |
This model was trained with SFT.
|
| 33 |
|
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime": 0.
|
| 5 |
"eval_samples": 10,
|
| 6 |
-
"eval_samples_per_second": 58.
|
| 7 |
-
"eval_steps_per_second": 11.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss":
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 10,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second": 1.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_loss": 0.0030517119448632,
|
| 4 |
+
"eval_runtime": 0.1724,
|
| 5 |
"eval_samples": 10,
|
| 6 |
+
"eval_samples_per_second": 58.01,
|
| 7 |
+
"eval_steps_per_second": 11.602,
|
| 8 |
+
"total_flos": 3352730995261440.0,
|
| 9 |
+
"train_loss": 0.9132046818675008,
|
| 10 |
+
"train_runtime": 21.9272,
|
| 11 |
"train_samples": 10,
|
| 12 |
+
"train_samples_per_second": 18.242,
|
| 13 |
+
"train_steps_per_second": 1.824
|
| 14 |
}
|
config.json
CHANGED
|
@@ -36,6 +36,6 @@
|
|
| 36 |
"tie_word_embeddings": true,
|
| 37 |
"torch_dtype": "bfloat16",
|
| 38 |
"transformers_version": "4.46.3",
|
| 39 |
-
"use_cache":
|
| 40 |
"vocab_size": 128256
|
| 41 |
}
|
|
|
|
| 36 |
"tie_word_embeddings": true,
|
| 37 |
"torch_dtype": "bfloat16",
|
| 38 |
"transformers_version": "4.46.3",
|
| 39 |
+
"use_cache": false,
|
| 40 |
"vocab_size": 128256
|
| 41 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime": 0.
|
| 5 |
"eval_samples": 10,
|
| 6 |
-
"eval_samples_per_second": 58.
|
| 7 |
-
"eval_steps_per_second": 11.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_loss": 0.0030517119448632,
|
| 4 |
+
"eval_runtime": 0.1724,
|
| 5 |
"eval_samples": 10,
|
| 6 |
+
"eval_samples_per_second": 58.01,
|
| 7 |
+
"eval_steps_per_second": 11.602
|
| 8 |
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4965799096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afb8bc60035e6f5c6b9aa9bc817024448f290884b8767593e9aecb1baf5f61bb
|
| 3 |
size 4965799096
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2247734992
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:364d194401bb4084b3ee664086eefd10bb5df26de57475f6344b62780ee2e7d9
|
| 3 |
size 2247734992
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fca926fdfedcb8fd225765fb3911e0ab5de0390ec7242a46dff829e8604f723
|
| 3 |
+
size 17210020
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 10,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second": 1.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"total_flos": 3352730995261440.0,
|
| 4 |
+
"train_loss": 0.9132046818675008,
|
| 5 |
+
"train_runtime": 21.9272,
|
| 6 |
"train_samples": 10,
|
| 7 |
+
"train_samples_per_second": 18.242,
|
| 8 |
+
"train_steps_per_second": 1.824
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,144 +1,626 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss": 1.
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 1.0,
|
| 19 |
-
"eval_loss": 1.
|
| 20 |
-
"eval_runtime": 0.
|
| 21 |
-
"eval_samples_per_second":
|
| 22 |
-
"eval_steps_per_second":
|
| 23 |
"step": 1
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 2.0,
|
| 27 |
-
"
|
| 28 |
-
"
|
|
|
|
| 29 |
"step": 2
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 2.0,
|
| 33 |
-
"eval_loss":
|
| 34 |
-
"eval_runtime": 0.
|
| 35 |
-
"eval_samples_per_second":
|
| 36 |
-
"eval_steps_per_second":
|
| 37 |
"step": 2
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 3.0,
|
| 41 |
-
"
|
| 42 |
-
"
|
|
|
|
| 43 |
"step": 3
|
| 44 |
},
|
| 45 |
{
|
| 46 |
"epoch": 3.0,
|
| 47 |
-
"eval_loss":
|
| 48 |
-
"eval_runtime": 0.
|
| 49 |
-
"eval_samples_per_second":
|
| 50 |
-
"eval_steps_per_second":
|
| 51 |
"step": 3
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 4.0,
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss":
|
| 58 |
"step": 4
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 4.0,
|
| 62 |
-
"eval_loss":
|
| 63 |
-
"eval_runtime": 0.
|
| 64 |
-
"eval_samples_per_second":
|
| 65 |
-
"eval_steps_per_second":
|
| 66 |
"step": 4
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 5.0,
|
| 70 |
-
"grad_norm":
|
| 71 |
-
"learning_rate":
|
| 72 |
-
"loss":
|
| 73 |
"step": 5
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 5.0,
|
| 77 |
-
"eval_loss":
|
| 78 |
-
"eval_runtime": 0.
|
| 79 |
-
"eval_samples_per_second":
|
| 80 |
-
"eval_steps_per_second":
|
| 81 |
"step": 5
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 6.0,
|
| 85 |
-
"grad_norm":
|
| 86 |
-
"learning_rate":
|
| 87 |
-
"loss":
|
| 88 |
"step": 6
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 6.0,
|
| 92 |
-
"eval_loss": 1.
|
| 93 |
-
"eval_runtime": 0.
|
| 94 |
-
"eval_samples_per_second":
|
| 95 |
-
"eval_steps_per_second":
|
| 96 |
"step": 6
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 7.0,
|
| 100 |
-
"grad_norm":
|
| 101 |
-
"learning_rate":
|
| 102 |
-
"loss": 1.
|
| 103 |
"step": 7
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"epoch": 7.0,
|
| 107 |
-
"eval_loss": 1.
|
| 108 |
-
"eval_runtime": 0.
|
| 109 |
-
"eval_samples_per_second":
|
| 110 |
-
"eval_steps_per_second":
|
| 111 |
"step": 7
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 8.0,
|
| 115 |
-
"grad_norm":
|
| 116 |
-
"learning_rate": 0.
|
| 117 |
-
"loss": 1.
|
| 118 |
"step": 8
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 8.0,
|
| 122 |
-
"eval_loss":
|
| 123 |
-
"eval_runtime": 0.
|
| 124 |
-
"eval_samples_per_second":
|
| 125 |
-
"eval_steps_per_second":
|
| 126 |
"step": 8
|
| 127 |
},
|
| 128 |
{
|
| 129 |
-
"epoch":
|
| 130 |
-
"
|
| 131 |
-
"
|
| 132 |
-
"
|
| 133 |
-
"
|
| 134 |
-
|
| 135 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 136 |
}
|
| 137 |
],
|
| 138 |
"logging_steps": 1,
|
| 139 |
-
"max_steps":
|
| 140 |
"num_input_tokens_seen": 0,
|
| 141 |
-
"num_train_epochs":
|
| 142 |
"save_steps": 500,
|
| 143 |
"stateful_callbacks": {
|
| 144 |
"TrainerControl": {
|
|
@@ -152,7 +634,7 @@
|
|
| 152 |
"attributes": {}
|
| 153 |
}
|
| 154 |
},
|
| 155 |
-
"total_flos":
|
| 156 |
"train_batch_size": 4,
|
| 157 |
"trial_name": null,
|
| 158 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 40,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"learning_rate": 2.5e-05,
|
| 14 |
+
"loss": 1.1193,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 1.0,
|
| 19 |
+
"eval_loss": 1.1183021068572998,
|
| 20 |
+
"eval_runtime": 0.097,
|
| 21 |
+
"eval_samples_per_second": 103.081,
|
| 22 |
+
"eval_steps_per_second": 20.616,
|
| 23 |
"step": 1
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 2.0,
|
| 27 |
+
"grad_norm": 19.4419002532959,
|
| 28 |
+
"learning_rate": 5e-05,
|
| 29 |
+
"loss": 1.1193,
|
| 30 |
"step": 2
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 2.0,
|
| 34 |
+
"eval_loss": 0.4163738191127777,
|
| 35 |
+
"eval_runtime": 0.0967,
|
| 36 |
+
"eval_samples_per_second": 103.452,
|
| 37 |
+
"eval_steps_per_second": 20.69,
|
| 38 |
"step": 2
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 3.0,
|
| 42 |
+
"grad_norm": 19.4419002532959,
|
| 43 |
+
"learning_rate": 7.500000000000001e-05,
|
| 44 |
+
"loss": 0.4152,
|
| 45 |
"step": 3
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 3.0,
|
| 49 |
+
"eval_loss": 0.4163738191127777,
|
| 50 |
+
"eval_runtime": 0.0975,
|
| 51 |
+
"eval_samples_per_second": 102.538,
|
| 52 |
+
"eval_steps_per_second": 20.508,
|
| 53 |
"step": 3
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"epoch": 4.0,
|
| 57 |
+
"grad_norm": 12.695544242858887,
|
| 58 |
+
"learning_rate": 0.0001,
|
| 59 |
+
"loss": 0.4152,
|
| 60 |
"step": 4
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 4.0,
|
| 64 |
+
"eval_loss": 0.8865498304367065,
|
| 65 |
+
"eval_runtime": 0.0966,
|
| 66 |
+
"eval_samples_per_second": 103.475,
|
| 67 |
+
"eval_steps_per_second": 20.695,
|
| 68 |
"step": 4
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 5.0,
|
| 72 |
+
"grad_norm": 12.695544242858887,
|
| 73 |
+
"learning_rate": 0.000125,
|
| 74 |
+
"loss": 0.8864,
|
| 75 |
"step": 5
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 5.0,
|
| 79 |
+
"eval_loss": 0.8865498304367065,
|
| 80 |
+
"eval_runtime": 0.0977,
|
| 81 |
+
"eval_samples_per_second": 102.389,
|
| 82 |
+
"eval_steps_per_second": 20.478,
|
| 83 |
"step": 5
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 6.0,
|
| 87 |
+
"grad_norm": 39.317420959472656,
|
| 88 |
+
"learning_rate": 0.00015000000000000001,
|
| 89 |
+
"loss": 0.8864,
|
| 90 |
"step": 6
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 6.0,
|
| 94 |
+
"eval_loss": 1.6666438579559326,
|
| 95 |
+
"eval_runtime": 0.0998,
|
| 96 |
+
"eval_samples_per_second": 100.229,
|
| 97 |
+
"eval_steps_per_second": 20.046,
|
| 98 |
"step": 6
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 7.0,
|
| 102 |
+
"grad_norm": 39.317420959472656,
|
| 103 |
+
"learning_rate": 0.000175,
|
| 104 |
+
"loss": 1.6618,
|
| 105 |
"step": 7
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 7.0,
|
| 109 |
+
"eval_loss": 1.6666438579559326,
|
| 110 |
+
"eval_runtime": 0.0975,
|
| 111 |
+
"eval_samples_per_second": 102.551,
|
| 112 |
+
"eval_steps_per_second": 20.51,
|
| 113 |
"step": 7
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 8.0,
|
| 117 |
+
"grad_norm": 44.225120544433594,
|
| 118 |
+
"learning_rate": 0.0002,
|
| 119 |
+
"loss": 1.6618,
|
| 120 |
"step": 8
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 8.0,
|
| 124 |
+
"eval_loss": 3.048259973526001,
|
| 125 |
+
"eval_runtime": 0.0983,
|
| 126 |
+
"eval_samples_per_second": 101.777,
|
| 127 |
+
"eval_steps_per_second": 20.355,
|
| 128 |
"step": 8
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 9.0,
|
| 132 |
+
"grad_norm": 44.225120544433594,
|
| 133 |
+
"learning_rate": 0.0001995184726672197,
|
| 134 |
+
"loss": 3.0505,
|
| 135 |
+
"step": 9
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 9.0,
|
| 139 |
+
"eval_loss": 3.048259973526001,
|
| 140 |
+
"eval_runtime": 0.0993,
|
| 141 |
+
"eval_samples_per_second": 100.727,
|
| 142 |
+
"eval_steps_per_second": 20.145,
|
| 143 |
+
"step": 9
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 10.0,
|
| 147 |
+
"grad_norm": 143.0501251220703,
|
| 148 |
+
"learning_rate": 0.00019807852804032305,
|
| 149 |
+
"loss": 3.0505,
|
| 150 |
+
"step": 10
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 10.0,
|
| 154 |
+
"eval_loss": 2.2029616832733154,
|
| 155 |
+
"eval_runtime": 0.097,
|
| 156 |
+
"eval_samples_per_second": 103.098,
|
| 157 |
+
"eval_steps_per_second": 20.62,
|
| 158 |
+
"step": 10
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 11.0,
|
| 162 |
+
"grad_norm": 143.0501251220703,
|
| 163 |
+
"learning_rate": 0.0001956940335732209,
|
| 164 |
+
"loss": 2.2026,
|
| 165 |
+
"step": 11
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 11.0,
|
| 169 |
+
"eval_loss": 2.2029616832733154,
|
| 170 |
+
"eval_runtime": 0.0976,
|
| 171 |
+
"eval_samples_per_second": 102.442,
|
| 172 |
+
"eval_steps_per_second": 20.488,
|
| 173 |
+
"step": 11
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 12.0,
|
| 177 |
+
"grad_norm": 27.46721076965332,
|
| 178 |
+
"learning_rate": 0.0001923879532511287,
|
| 179 |
+
"loss": 2.2026,
|
| 180 |
+
"step": 12
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 12.0,
|
| 184 |
+
"eval_loss": 2.8971307277679443,
|
| 185 |
+
"eval_runtime": 0.0976,
|
| 186 |
+
"eval_samples_per_second": 102.486,
|
| 187 |
+
"eval_steps_per_second": 20.497,
|
| 188 |
+
"step": 12
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 13.0,
|
| 192 |
+
"grad_norm": 27.46721076965332,
|
| 193 |
+
"learning_rate": 0.0001881921264348355,
|
| 194 |
+
"loss": 2.9002,
|
| 195 |
+
"step": 13
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 13.0,
|
| 199 |
+
"eval_loss": 2.8971307277679443,
|
| 200 |
+
"eval_runtime": 0.0973,
|
| 201 |
+
"eval_samples_per_second": 102.809,
|
| 202 |
+
"eval_steps_per_second": 20.562,
|
| 203 |
+
"step": 13
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 14.0,
|
| 207 |
+
"grad_norm": 49.42749786376953,
|
| 208 |
+
"learning_rate": 0.00018314696123025454,
|
| 209 |
+
"loss": 2.9002,
|
| 210 |
+
"step": 14
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 14.0,
|
| 214 |
+
"eval_loss": 3.4301562309265137,
|
| 215 |
+
"eval_runtime": 0.0984,
|
| 216 |
+
"eval_samples_per_second": 101.612,
|
| 217 |
+
"eval_steps_per_second": 20.322,
|
| 218 |
+
"step": 14
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 15.0,
|
| 222 |
+
"grad_norm": 49.42749786376953,
|
| 223 |
+
"learning_rate": 0.0001773010453362737,
|
| 224 |
+
"loss": 3.4308,
|
| 225 |
+
"step": 15
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 15.0,
|
| 229 |
+
"eval_loss": 3.4301562309265137,
|
| 230 |
+
"eval_runtime": 0.0981,
|
| 231 |
+
"eval_samples_per_second": 101.972,
|
| 232 |
+
"eval_steps_per_second": 20.394,
|
| 233 |
+
"step": 15
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 16.0,
|
| 237 |
+
"grad_norm": 46.989479064941406,
|
| 238 |
+
"learning_rate": 0.00017071067811865476,
|
| 239 |
+
"loss": 3.4308,
|
| 240 |
+
"step": 16
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 16.0,
|
| 244 |
+
"eval_loss": 1.4099053144454956,
|
| 245 |
+
"eval_runtime": 0.0973,
|
| 246 |
+
"eval_samples_per_second": 102.796,
|
| 247 |
+
"eval_steps_per_second": 20.559,
|
| 248 |
+
"step": 16
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 17.0,
|
| 252 |
+
"grad_norm": 46.989479064941406,
|
| 253 |
+
"learning_rate": 0.00016343932841636456,
|
| 254 |
+
"loss": 1.4133,
|
| 255 |
+
"step": 17
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 17.0,
|
| 259 |
+
"eval_loss": 1.4099053144454956,
|
| 260 |
+
"eval_runtime": 0.097,
|
| 261 |
+
"eval_samples_per_second": 103.061,
|
| 262 |
+
"eval_steps_per_second": 20.612,
|
| 263 |
+
"step": 17
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 18.0,
|
| 267 |
+
"grad_norm": 19.974260330200195,
|
| 268 |
+
"learning_rate": 0.00015555702330196023,
|
| 269 |
+
"loss": 1.4133,
|
| 270 |
+
"step": 18
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 18.0,
|
| 274 |
+
"eval_loss": 0.7468957304954529,
|
| 275 |
+
"eval_runtime": 0.0986,
|
| 276 |
+
"eval_samples_per_second": 101.448,
|
| 277 |
+
"eval_steps_per_second": 20.29,
|
| 278 |
+
"step": 18
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 19.0,
|
| 282 |
+
"grad_norm": 19.974260330200195,
|
| 283 |
+
"learning_rate": 0.0001471396736825998,
|
| 284 |
+
"loss": 0.746,
|
| 285 |
+
"step": 19
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 19.0,
|
| 289 |
+
"eval_loss": 0.7468957304954529,
|
| 290 |
+
"eval_runtime": 0.0972,
|
| 291 |
+
"eval_samples_per_second": 102.877,
|
| 292 |
+
"eval_steps_per_second": 20.575,
|
| 293 |
+
"step": 19
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 20.0,
|
| 297 |
+
"grad_norm": 9.610711097717285,
|
| 298 |
+
"learning_rate": 0.000138268343236509,
|
| 299 |
+
"loss": 0.746,
|
| 300 |
+
"step": 20
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 20.0,
|
| 304 |
+
"eval_loss": 0.16501614451408386,
|
| 305 |
+
"eval_runtime": 0.1002,
|
| 306 |
+
"eval_samples_per_second": 99.82,
|
| 307 |
+
"eval_steps_per_second": 19.964,
|
| 308 |
+
"step": 20
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 21.0,
|
| 312 |
+
"grad_norm": 9.610711097717285,
|
| 313 |
+
"learning_rate": 0.00012902846772544624,
|
| 314 |
+
"loss": 0.1654,
|
| 315 |
+
"step": 21
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 21.0,
|
| 319 |
+
"eval_loss": 0.16501614451408386,
|
| 320 |
+
"eval_runtime": 0.0976,
|
| 321 |
+
"eval_samples_per_second": 102.477,
|
| 322 |
+
"eval_steps_per_second": 20.495,
|
| 323 |
+
"step": 21
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 22.0,
|
| 327 |
+
"grad_norm": 3.4515697956085205,
|
| 328 |
+
"learning_rate": 0.00011950903220161285,
|
| 329 |
+
"loss": 0.1654,
|
| 330 |
+
"step": 22
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 22.0,
|
| 334 |
+
"eval_loss": 0.14767812192440033,
|
| 335 |
+
"eval_runtime": 0.097,
|
| 336 |
+
"eval_samples_per_second": 103.11,
|
| 337 |
+
"eval_steps_per_second": 20.622,
|
| 338 |
+
"step": 22
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 23.0,
|
| 342 |
+
"grad_norm": 3.4515697956085205,
|
| 343 |
+
"learning_rate": 0.0001098017140329561,
|
| 344 |
+
"loss": 0.1474,
|
| 345 |
+
"step": 23
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 23.0,
|
| 349 |
+
"eval_loss": 0.14767812192440033,
|
| 350 |
+
"eval_runtime": 0.1041,
|
| 351 |
+
"eval_samples_per_second": 96.05,
|
| 352 |
+
"eval_steps_per_second": 19.21,
|
| 353 |
+
"step": 23
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 24.0,
|
| 357 |
+
"grad_norm": 4.262996196746826,
|
| 358 |
+
"learning_rate": 0.0001,
|
| 359 |
+
"loss": 0.1474,
|
| 360 |
+
"step": 24
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 24.0,
|
| 364 |
+
"eval_loss": 0.05527349188923836,
|
| 365 |
+
"eval_runtime": 0.0983,
|
| 366 |
+
"eval_samples_per_second": 101.742,
|
| 367 |
+
"eval_steps_per_second": 20.348,
|
| 368 |
+
"step": 24
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 25.0,
|
| 372 |
+
"grad_norm": 4.262996196746826,
|
| 373 |
+
"learning_rate": 9.019828596704394e-05,
|
| 374 |
+
"loss": 0.0569,
|
| 375 |
+
"step": 25
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 25.0,
|
| 379 |
+
"eval_loss": 0.05527349188923836,
|
| 380 |
+
"eval_runtime": 0.1002,
|
| 381 |
+
"eval_samples_per_second": 99.795,
|
| 382 |
+
"eval_steps_per_second": 19.959,
|
| 383 |
+
"step": 25
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 26.0,
|
| 387 |
+
"grad_norm": 2.504621744155884,
|
| 388 |
+
"learning_rate": 8.049096779838719e-05,
|
| 389 |
+
"loss": 0.0569,
|
| 390 |
+
"step": 26
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 26.0,
|
| 394 |
+
"eval_loss": 0.05637549236416817,
|
| 395 |
+
"eval_runtime": 0.1041,
|
| 396 |
+
"eval_samples_per_second": 96.026,
|
| 397 |
+
"eval_steps_per_second": 19.205,
|
| 398 |
+
"step": 26
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 27.0,
|
| 402 |
+
"grad_norm": 2.504621744155884,
|
| 403 |
+
"learning_rate": 7.097153227455379e-05,
|
| 404 |
+
"loss": 0.0575,
|
| 405 |
+
"step": 27
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 27.0,
|
| 409 |
+
"eval_loss": 0.05637549236416817,
|
| 410 |
+
"eval_runtime": 0.0973,
|
| 411 |
+
"eval_samples_per_second": 102.725,
|
| 412 |
+
"eval_steps_per_second": 20.545,
|
| 413 |
+
"step": 27
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 28.0,
|
| 417 |
+
"grad_norm": 3.5743298530578613,
|
| 418 |
+
"learning_rate": 6.173165676349103e-05,
|
| 419 |
+
"loss": 0.0575,
|
| 420 |
+
"step": 28
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 28.0,
|
| 424 |
+
"eval_loss": 0.003984498791396618,
|
| 425 |
+
"eval_runtime": 0.0975,
|
| 426 |
+
"eval_samples_per_second": 102.605,
|
| 427 |
+
"eval_steps_per_second": 20.521,
|
| 428 |
+
"step": 28
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 29.0,
|
| 432 |
+
"grad_norm": 3.5743298530578613,
|
| 433 |
+
"learning_rate": 5.286032631740023e-05,
|
| 434 |
+
"loss": 0.0041,
|
| 435 |
+
"step": 29
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 29.0,
|
| 439 |
+
"eval_loss": 0.003984498791396618,
|
| 440 |
+
"eval_runtime": 0.0979,
|
| 441 |
+
"eval_samples_per_second": 102.094,
|
| 442 |
+
"eval_steps_per_second": 20.419,
|
| 443 |
+
"step": 29
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 30.0,
|
| 447 |
+
"grad_norm": 0.1635422706604004,
|
| 448 |
+
"learning_rate": 4.444297669803981e-05,
|
| 449 |
+
"loss": 0.0041,
|
| 450 |
+
"step": 30
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 30.0,
|
| 454 |
+
"eval_loss": 0.0021899878047406673,
|
| 455 |
+
"eval_runtime": 0.098,
|
| 456 |
+
"eval_samples_per_second": 102.061,
|
| 457 |
+
"eval_steps_per_second": 20.412,
|
| 458 |
+
"step": 30
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 31.0,
|
| 462 |
+
"grad_norm": 0.1635422706604004,
|
| 463 |
+
"learning_rate": 3.6560671583635467e-05,
|
| 464 |
+
"loss": 0.0022,
|
| 465 |
+
"step": 31
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 31.0,
|
| 469 |
+
"eval_loss": 0.0021899878047406673,
|
| 470 |
+
"eval_runtime": 0.0971,
|
| 471 |
+
"eval_samples_per_second": 103.036,
|
| 472 |
+
"eval_steps_per_second": 20.607,
|
| 473 |
+
"step": 31
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 32.0,
|
| 477 |
+
"grad_norm": 0.0847228392958641,
|
| 478 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 479 |
+
"loss": 0.0022,
|
| 480 |
+
"step": 32
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 32.0,
|
| 484 |
+
"eval_loss": 0.0015291140880435705,
|
| 485 |
+
"eval_runtime": 0.1006,
|
| 486 |
+
"eval_samples_per_second": 99.357,
|
| 487 |
+
"eval_steps_per_second": 19.871,
|
| 488 |
+
"step": 32
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 33.0,
|
| 492 |
+
"grad_norm": 0.0847228392958641,
|
| 493 |
+
"learning_rate": 2.26989546637263e-05,
|
| 494 |
+
"loss": 0.0015,
|
| 495 |
+
"step": 33
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 33.0,
|
| 499 |
+
"eval_loss": 0.0015291140880435705,
|
| 500 |
+
"eval_runtime": 0.1027,
|
| 501 |
+
"eval_samples_per_second": 97.387,
|
| 502 |
+
"eval_steps_per_second": 19.477,
|
| 503 |
+
"step": 33
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 34.0,
|
| 507 |
+
"grad_norm": 0.06535077840089798,
|
| 508 |
+
"learning_rate": 1.6853038769745467e-05,
|
| 509 |
+
"loss": 0.0015,
|
| 510 |
+
"step": 34
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 34.0,
|
| 514 |
+
"eval_loss": 0.0011607444612309337,
|
| 515 |
+
"eval_runtime": 0.0977,
|
| 516 |
+
"eval_samples_per_second": 102.397,
|
| 517 |
+
"eval_steps_per_second": 20.479,
|
| 518 |
+
"step": 34
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 35.0,
|
| 522 |
+
"grad_norm": 0.06535077840089798,
|
| 523 |
+
"learning_rate": 1.1807873565164506e-05,
|
| 524 |
+
"loss": 0.0011,
|
| 525 |
+
"step": 35
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 35.0,
|
| 529 |
+
"eval_loss": 0.0011607444612309337,
|
| 530 |
+
"eval_runtime": 0.0971,
|
| 531 |
+
"eval_samples_per_second": 102.985,
|
| 532 |
+
"eval_steps_per_second": 20.597,
|
| 533 |
+
"step": 35
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 36.0,
|
| 537 |
+
"grad_norm": 0.04596730321645737,
|
| 538 |
+
"learning_rate": 7.612046748871327e-06,
|
| 539 |
+
"loss": 0.0011,
|
| 540 |
+
"step": 36
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 36.0,
|
| 544 |
+
"eval_loss": 0.0010076254839077592,
|
| 545 |
+
"eval_runtime": 0.0972,
|
| 546 |
+
"eval_samples_per_second": 102.913,
|
| 547 |
+
"eval_steps_per_second": 20.583,
|
| 548 |
+
"step": 36
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 37.0,
|
| 552 |
+
"grad_norm": 0.04596730321645737,
|
| 553 |
+
"learning_rate": 4.305966426779118e-06,
|
| 554 |
+
"loss": 0.001,
|
| 555 |
+
"step": 37
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 37.0,
|
| 559 |
+
"eval_loss": 0.0010076254839077592,
|
| 560 |
+
"eval_runtime": 0.097,
|
| 561 |
+
"eval_samples_per_second": 103.097,
|
| 562 |
+
"eval_steps_per_second": 20.619,
|
| 563 |
+
"step": 37
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 38.0,
|
| 567 |
+
"grad_norm": 0.039849672466516495,
|
| 568 |
+
"learning_rate": 1.921471959676957e-06,
|
| 569 |
+
"loss": 0.001,
|
| 570 |
+
"step": 38
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 38.0,
|
| 574 |
+
"eval_loss": 0.0009246615809388459,
|
| 575 |
+
"eval_runtime": 0.0975,
|
| 576 |
+
"eval_samples_per_second": 102.584,
|
| 577 |
+
"eval_steps_per_second": 20.517,
|
| 578 |
+
"step": 38
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 39.0,
|
| 582 |
+
"grad_norm": 0.039849672466516495,
|
| 583 |
+
"learning_rate": 4.815273327803182e-07,
|
| 584 |
+
"loss": 0.0009,
|
| 585 |
+
"step": 39
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 39.0,
|
| 589 |
+
"eval_loss": 0.0009246615809388459,
|
| 590 |
+
"eval_runtime": 0.099,
|
| 591 |
+
"eval_samples_per_second": 101.052,
|
| 592 |
+
"eval_steps_per_second": 20.21,
|
| 593 |
+
"step": 39
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 40.0,
|
| 597 |
+
"grad_norm": 0.037203624844551086,
|
| 598 |
+
"learning_rate": 0.0,
|
| 599 |
+
"loss": 0.0009,
|
| 600 |
+
"step": 40
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 40.0,
|
| 604 |
+
"eval_loss": 0.0009156091255135834,
|
| 605 |
+
"eval_runtime": 0.0977,
|
| 606 |
+
"eval_samples_per_second": 102.33,
|
| 607 |
+
"eval_steps_per_second": 20.466,
|
| 608 |
+
"step": 40
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 40.0,
|
| 612 |
+
"step": 40,
|
| 613 |
+
"total_flos": 3352730995261440.0,
|
| 614 |
+
"train_loss": 0.9132046818675008,
|
| 615 |
+
"train_runtime": 21.9272,
|
| 616 |
+
"train_samples_per_second": 18.242,
|
| 617 |
+
"train_steps_per_second": 1.824
|
| 618 |
}
|
| 619 |
],
|
| 620 |
"logging_steps": 1,
|
| 621 |
+
"max_steps": 40,
|
| 622 |
"num_input_tokens_seen": 0,
|
| 623 |
+
"num_train_epochs": 40,
|
| 624 |
"save_steps": 500,
|
| 625 |
"stateful_callbacks": {
|
| 626 |
"TrainerControl": {
|
|
|
|
| 634 |
"attributes": {}
|
| 635 |
}
|
| 636 |
},
|
| 637 |
+
"total_flos": 3352730995261440.0,
|
| 638 |
"train_batch_size": 4,
|
| 639 |
"trial_name": null,
|
| 640 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa2c887c5cce835e5cbf3d2e0b70db81040dda2b3369db7f54f3b1f24d181091
|
| 3 |
size 6968
|