Upload folder using huggingface_hub

adapter_config.json

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "qkv_proj",
+    "gate_up_proj",
     "o_proj",
-    "down_proj",
-    "gate_up_proj"
+    "qkv_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913183eb557caacb7d03d3dd3efd47e502fcad2e6bcdf3d65db1c91b57ee4f8d
+oid sha256:67cfeac19a2419a44a38965724a3e10984b3cfb02dc513e9d9c24a26148c9165
 size 100697728

all_results.json

@@ -1,13 +1,8 @@
 {
-    "epoch": 4.173913043478261,
-    "eval_loss": 0.6318144798278809,
-    "eval_runtime": 3.9163,
-    "eval_samples": 20,
-    "eval_samples_per_second": 5.107,
-    "eval_steps_per_second": 0.766,
-    "total_flos": 2.8914967713060864e+16,
-    "train_loss": 0.6689150285720825,
-    "train_runtime": 536.5173,
-    "train_samples_per_second": 1.491,
-    "train_steps_per_second": 0.093
+    "epoch": 27.0,
+    "total_flos": 1.3785203655910195e+17,
+    "train_loss": 0.12853161850599226,
+    "train_runtime": 2497.1205,
+    "train_samples_per_second": 1.802,
+    "train_steps_per_second": 0.108
 }

checkpoint-270/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-270/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_up_proj",
+    "o_proj",
+    "qkv_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-270/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cfeac19a2419a44a38965724a3e10984b3cfb02dc513e9d9c24a26148c9165
+size 100697728

checkpoint-270/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-270/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665a910cd2427b6ae373042170c8d9f4658e1d770d549dc74bc1fae5abd93c8b
+size 201541754

checkpoint-270/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b65aed2681ea28e05cb2b3e7c473b8d8f5588b800eb988a339fee01ab2a1a09
+size 14244

checkpoint-270/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b6d8436a3a108ca5e2794dbbf8cfa1e36b8e16cff066458b055056a187fb3b
+size 1064

checkpoint-270/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-270/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-270/tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-270/trainer_state.json

@@ -0,0 +1,412 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 27.0,
+  "eval_steps": 500,
+  "global_step": 270,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.3464358448982239,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 0.7933,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2775850296020508,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 0.6763,
+      "step": 10
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.20196351408958435,
+      "learning_rate": 0.00019999247018391447,
+      "loss": 0.612,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.20944692194461823,
+      "learning_rate": 0.00019972904566786903,
+      "loss": 0.593,
+      "step": 20
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.1796199381351471,
+      "learning_rate": 0.000199090263542778,
+      "loss": 0.528,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3253108859062195,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 0.4901,
+      "step": 30
+    },
+    {
+      "epoch": 3.533333333333333,
+      "grad_norm": 0.2155134528875351,
+      "learning_rate": 0.00019669764710448522,
+      "loss": 0.4385,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.40249642729759216,
+      "learning_rate": 0.00019495281805930367,
+      "loss": 0.4146,
+      "step": 40
+    },
+    {
+      "epoch": 4.533333333333333,
+      "grad_norm": 0.21931566298007965,
+      "learning_rate": 0.00019285060804732158,
+      "loss": 0.3422,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.47045040130615234,
+      "learning_rate": 0.00019039892931234435,
+      "loss": 0.334,
+      "step": 50
+    },
+    {
+      "epoch": 5.533333333333333,
+      "grad_norm": 0.33896583318710327,
+      "learning_rate": 0.00018760700941954065,
+      "loss": 0.3055,
+      "step": 55
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.6106130480766296,
+      "learning_rate": 0.00018448535652497073,
+      "loss": 0.2364,
+      "step": 60
+    },
+    {
+      "epoch": 6.533333333333333,
+      "grad_norm": 0.34181615710258484,
+      "learning_rate": 0.0001810457198252595,
+      "loss": 0.19,
+      "step": 65
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8446937799453735,
+      "learning_rate": 0.0001773010453362737,
+      "loss": 0.1965,
+      "step": 70
+    },
+    {
+      "epoch": 7.533333333333333,
+      "grad_norm": 0.5083507299423218,
+      "learning_rate": 0.00017326542716724128,
+      "loss": 0.1207,
+      "step": 75
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.7833607196807861,
+      "learning_rate": 0.0001689540544737067,
+      "loss": 0.1283,
+      "step": 80
+    },
+    {
+      "epoch": 8.533333333333333,
+      "grad_norm": 0.3553655743598938,
+      "learning_rate": 0.00016438315428897915,
+      "loss": 0.0811,
+      "step": 85
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.7091866135597229,
+      "learning_rate": 0.00015956993044924334,
+      "loss": 0.0802,
+      "step": 90
+    },
+    {
+      "epoch": 9.533333333333333,
+      "grad_norm": 0.43794405460357666,
+      "learning_rate": 0.00015453249884220464,
+      "loss": 0.0492,
+      "step": 95
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.5798842310905457,
+      "learning_rate": 0.00014928981922297842,
+      "loss": 0.0524,
+      "step": 100
+    },
+    {
+      "epoch": 10.533333333333333,
+      "grad_norm": 0.3912927210330963,
+      "learning_rate": 0.00014386162385385278,
+      "loss": 0.0302,
+      "step": 105
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.4159412682056427,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.0328,
+      "step": 110
+    },
+    {
+      "epoch": 11.533333333333333,
+      "grad_norm": 0.24435237050056458,
+      "learning_rate": 0.0001325310292162263,
+      "loss": 0.0239,
+      "step": 115
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.24223262071609497,
+      "learning_rate": 0.00012667127574748986,
+      "loss": 0.0171,
+      "step": 120
+    },
+    {
+      "epoch": 12.533333333333333,
+      "grad_norm": 0.1762484759092331,
+      "learning_rate": 0.00012071113761922186,
+      "loss": 0.0135,
+      "step": 125
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.28046339750289917,
+      "learning_rate": 0.00011467304744553618,
+      "loss": 0.0143,
+      "step": 130
+    },
+    {
+      "epoch": 13.533333333333333,
+      "grad_norm": 0.28064408898353577,
+      "learning_rate": 0.000108579731234444,
+      "loss": 0.0128,
+      "step": 135
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.19103752076625824,
+      "learning_rate": 0.00010245412285229124,
+      "loss": 0.0101,
+      "step": 140
+    },
+    {
+      "epoch": 14.533333333333333,
+      "grad_norm": 0.2761705815792084,
+      "learning_rate": 9.631927770586412e-05,
+      "loss": 0.0096,
+      "step": 145
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.3451383709907532,
+      "learning_rate": 9.019828596704394e-05,
+      "loss": 0.0084,
+      "step": 150
+    },
+    {
+      "epoch": 15.533333333333333,
+      "grad_norm": 0.22912859916687012,
+      "learning_rate": 8.411418566661388e-05,
+      "loss": 0.0087,
+      "step": 155
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.2961307466030121,
+      "learning_rate": 7.808987598431303e-05,
+      "loss": 0.0054,
+      "step": 160
+    },
+    {
+      "epoch": 16.533333333333335,
+      "grad_norm": 0.05174371972680092,
+      "learning_rate": 7.21480310614947e-05,
+      "loss": 0.0037,
+      "step": 165
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.6668692827224731,
+      "learning_rate": 6.6311014660778e-05,
+      "loss": 0.0086,
+      "step": 170
+    },
+    {
+      "epoch": 17.533333333333335,
+      "grad_norm": 0.0423920676112175,
+      "learning_rate": 6.060079599389521e-05,
+      "loss": 0.0046,
+      "step": 175
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.048323437571525574,
+      "learning_rate": 5.503886703453933e-05,
+      "loss": 0.005,
+      "step": 180
+    },
+    {
+      "epoch": 18.533333333333335,
+      "grad_norm": 0.14866454899311066,
+      "learning_rate": 4.964616162742826e-05,
+      "loss": 0.0039,
+      "step": 185
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.04198712110519409,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0033,
+      "step": 190
+    },
+    {
+      "epoch": 19.533333333333335,
+      "grad_norm": 0.037916265428066254,
+      "learning_rate": 3.944889585956746e-05,
+      "loss": 0.0075,
+      "step": 195
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.031426794826984406,
+      "learning_rate": 3.468271570462235e-05,
+      "loss": 0.0036,
+      "step": 200
+    },
+    {
+      "epoch": 20.533333333333335,
+      "grad_norm": 0.1819785088300705,
+      "learning_rate": 3.016237505910272e-05,
+      "loss": 0.0062,
+      "step": 205
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 0.09462948143482208,
+      "learning_rate": 2.5904887464504114e-05,
+      "loss": 0.0034,
+      "step": 210
+    },
+    {
+      "epoch": 21.533333333333335,
+      "grad_norm": 0.11672957241535187,
+      "learning_rate": 2.1926277142790552e-05,
+      "loss": 0.0025,
+      "step": 215
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.04571106657385826,
+      "learning_rate": 1.824151868484164e-05,
+      "loss": 0.0042,
+      "step": 220
+    },
+    {
+      "epoch": 22.533333333333335,
+      "grad_norm": 0.019737839698791504,
+      "learning_rate": 1.486448068947348e-05,
+      "loss": 0.0021,
+      "step": 225
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.03002820909023285,
+      "learning_rate": 1.1807873565164506e-05,
+      "loss": 0.0049,
+      "step": 230
+    },
+    {
+      "epoch": 23.533333333333335,
+      "grad_norm": 0.24355602264404297,
+      "learning_rate": 9.083201690947763e-06,
+      "loss": 0.004,
+      "step": 235
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.035868410021066666,
+      "learning_rate": 6.700720116526116e-06,
+      "loss": 0.0024,
+      "step": 240
+    },
+    {
+      "epoch": 24.533333333333335,
+      "grad_norm": 0.029756512492895126,
+      "learning_rate": 4.669395964580614e-06,
+      "loss": 0.0025,
+      "step": 245
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.2836012542247772,
+      "learning_rate": 2.996874680545603e-06,
+      "loss": 0.0059,
+      "step": 250
+    },
+    {
+      "epoch": 25.533333333333335,
+      "grad_norm": 0.2209901213645935,
+      "learning_rate": 1.6894512568783716e-06,
+      "loss": 0.004,
+      "step": 255
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 0.023770242929458618,
+      "learning_rate": 7.520465401290033e-07,
+      "loss": 0.0033,
+      "step": 260
+    },
+    {
+      "epoch": 26.533333333333335,
+      "grad_norm": 0.02641889452934265,
+      "learning_rate": 1.8818870998508208e-07,
+      "loss": 0.0032,
+      "step": 265
+    },
+    {
+      "epoch": 27.0,
+      "grad_norm": 0.03176680952310562,
+      "learning_rate": 0.0,
+      "loss": 0.0025,
+      "step": 270
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3785203655910195e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-270/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a98014c58d55a004fcf6f633921d0efe54b1543b60e7ac340ed1a1b1f40acb7
+size 5624

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.173913043478261,
-    "total_flos": 2.8914967713060864e+16,
-    "train_loss": 0.6689150285720825,
-    "train_runtime": 536.5173,
-    "train_samples_per_second": 1.491,
-    "train_steps_per_second": 0.093
+    "epoch": 27.0,
+    "total_flos": 1.3785203655910195e+17,
+    "train_loss": 0.12853161850599226,
+    "train_runtime": 2497.1205,
+    "train_samples_per_second": 1.802,
+    "train_steps_per_second": 0.108
 }

trainer_state.json

@@ -1,138 +1,406 @@
 {
-  "best_global_step": 48,
-  "best_metric": 0.6318144798278809,
-  "best_model_checkpoint": "//outputs/task7_microsoft/Phi-3.5-mini-instruct/checkpoint-48",
-  "epoch": 4.173913043478261,
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 27.0,
   "eval_steps": 500,
-  "global_step": 50,
+  "global_step": 270,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.43478260869565216,
-      "grad_norm": 0.3567487597465515,
-      "learning_rate": 4e-05,
-      "loss": 0.7927,
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.3464358448982239,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 0.7933,
       "step": 5
     },
-    {
-      "epoch": 0.8695652173913043,
-      "grad_norm": 0.20804046094417572,
-      "learning_rate": 8e-05,
-      "loss": 0.877,
-      "step": 10
-    },
     {
       "epoch": 1.0,
-      "eval_loss": 0.7741447687149048,
-      "eval_runtime": 3.8872,
-      "eval_samples_per_second": 5.145,
-      "eval_steps_per_second": 0.772,
-      "step": 12
+      "grad_norm": 0.2775850296020508,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 0.6763,
+      "step": 10
     },
     {
-      "epoch": 1.2608695652173914,
-      "grad_norm": 0.14667491614818573,
-      "learning_rate": 0.00012,
-      "loss": 0.797,
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.20196351408958435,
+      "learning_rate": 0.00019999247018391447,
+      "loss": 0.612,
       "step": 15
     },
-    {
-      "epoch": 1.6956521739130435,
-      "grad_norm": 0.18651264905929565,
-      "learning_rate": 0.00016,
-      "loss": 0.6654,
-      "step": 20
-    },
     {
       "epoch": 2.0,
-      "eval_loss": 0.6869648694992065,
-      "eval_runtime": 3.8967,
-      "eval_samples_per_second": 5.132,
-      "eval_steps_per_second": 0.77,
-      "step": 24
+      "grad_norm": 0.20944692194461823,
+      "learning_rate": 0.00019972904566786903,
+      "loss": 0.593,
+      "step": 20
     },
     {
-      "epoch": 2.0869565217391304,
-      "grad_norm": 0.18070296943187714,
-      "learning_rate": 0.0002,
-      "loss": 0.6351,
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.1796199381351471,
+      "learning_rate": 0.000199090263542778,
+      "loss": 0.528,
       "step": 25
     },
     {
-      "epoch": 2.5217391304347827,
-      "grad_norm": 0.23248770833015442,
-      "learning_rate": 0.00018090169943749476,
-      "loss": 0.6273,
+      "epoch": 3.0,
+      "grad_norm": 0.3253108859062195,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 0.4901,
       "step": 30
     },
     {
-      "epoch": 2.9565217391304346,
-      "grad_norm": 0.19235172867774963,
-      "learning_rate": 0.00013090169943749476,
-      "loss": 0.599,
+      "epoch": 3.533333333333333,
+      "grad_norm": 0.2155134528875351,
+      "learning_rate": 0.00019669764710448522,
+      "loss": 0.4385,
       "step": 35
     },
     {
-      "epoch": 3.0,
-      "eval_loss": 0.6456981301307678,
-      "eval_runtime": 3.8903,
-      "eval_samples_per_second": 5.141,
-      "eval_steps_per_second": 0.771,
-      "step": 36
-    },
-    {
-      "epoch": 3.3478260869565215,
-      "grad_norm": 0.18532131612300873,
-      "learning_rate": 6.909830056250527e-05,
-      "loss": 0.5887,
+      "epoch": 4.0,
+      "grad_norm": 0.40249642729759216,
+      "learning_rate": 0.00019495281805930367,
+      "loss": 0.4146,
       "step": 40
     },
     {
-      "epoch": 3.782608695652174,
-      "grad_norm": 0.23707902431488037,
-      "learning_rate": 1.9098300562505266e-05,
-      "loss": 0.5482,
+      "epoch": 4.533333333333333,
+      "grad_norm": 0.21931566298007965,
+      "learning_rate": 0.00019285060804732158,
+      "loss": 0.3422,
       "step": 45
     },
     {
-      "epoch": 4.0,
-      "eval_loss": 0.6318144798278809,
-      "eval_runtime": 3.8893,
-      "eval_samples_per_second": 5.142,
-      "eval_steps_per_second": 0.771,
-      "step": 48
+      "epoch": 5.0,
+      "grad_norm": 0.47045040130615234,
+      "learning_rate": 0.00019039892931234435,
+      "loss": 0.334,
+      "step": 50
     },
     {
-      "epoch": 4.173913043478261,
-      "grad_norm": 0.20858274400234222,
-      "learning_rate": 0.0,
-      "loss": 0.5586,
-      "step": 50
+      "epoch": 5.533333333333333,
+      "grad_norm": 0.33896583318710327,
+      "learning_rate": 0.00018760700941954065,
+      "loss": 0.3055,
+      "step": 55
     },
     {
-      "epoch": 4.173913043478261,
-      "eval_loss": 0.6320340037345886,
-      "eval_runtime": 3.8925,
-      "eval_samples_per_second": 5.138,
-      "eval_steps_per_second": 0.771,
-      "step": 50
+      "epoch": 6.0,
+      "grad_norm": 0.6106130480766296,
+      "learning_rate": 0.00018448535652497073,
+      "loss": 0.2364,
+      "step": 60
+    },
+    {
+      "epoch": 6.533333333333333,
+      "grad_norm": 0.34181615710258484,
+      "learning_rate": 0.0001810457198252595,
+      "loss": 0.19,
+      "step": 65
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8446937799453735,
+      "learning_rate": 0.0001773010453362737,
+      "loss": 0.1965,
+      "step": 70
+    },
+    {
+      "epoch": 7.533333333333333,
+      "grad_norm": 0.5083507299423218,
+      "learning_rate": 0.00017326542716724128,
+      "loss": 0.1207,
+      "step": 75
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.7833607196807861,
+      "learning_rate": 0.0001689540544737067,
+      "loss": 0.1283,
+      "step": 80
+    },
+    {
+      "epoch": 8.533333333333333,
+      "grad_norm": 0.3553655743598938,
+      "learning_rate": 0.00016438315428897915,
+      "loss": 0.0811,
+      "step": 85
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.7091866135597229,
+      "learning_rate": 0.00015956993044924334,
+      "loss": 0.0802,
+      "step": 90
+    },
+    {
+      "epoch": 9.533333333333333,
+      "grad_norm": 0.43794405460357666,
+      "learning_rate": 0.00015453249884220464,
+      "loss": 0.0492,
+      "step": 95
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.5798842310905457,
+      "learning_rate": 0.00014928981922297842,
+      "loss": 0.0524,
+      "step": 100
+    },
+    {
+      "epoch": 10.533333333333333,
+      "grad_norm": 0.3912927210330963,
+      "learning_rate": 0.00014386162385385278,
+      "loss": 0.0302,
+      "step": 105
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.4159412682056427,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.0328,
+      "step": 110
+    },
+    {
+      "epoch": 11.533333333333333,
+      "grad_norm": 0.24435237050056458,
+      "learning_rate": 0.0001325310292162263,
+      "loss": 0.0239,
+      "step": 115
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.24223262071609497,
+      "learning_rate": 0.00012667127574748986,
+      "loss": 0.0171,
+      "step": 120
+    },
+    {
+      "epoch": 12.533333333333333,
+      "grad_norm": 0.1762484759092331,
+      "learning_rate": 0.00012071113761922186,
+      "loss": 0.0135,
+      "step": 125
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.28046339750289917,
+      "learning_rate": 0.00011467304744553618,
+      "loss": 0.0143,
+      "step": 130
+    },
+    {
+      "epoch": 13.533333333333333,
+      "grad_norm": 0.28064408898353577,
+      "learning_rate": 0.000108579731234444,
+      "loss": 0.0128,
+      "step": 135
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.19103752076625824,
+      "learning_rate": 0.00010245412285229124,
+      "loss": 0.0101,
+      "step": 140
+    },
+    {
+      "epoch": 14.533333333333333,
+      "grad_norm": 0.2761705815792084,
+      "learning_rate": 9.631927770586412e-05,
+      "loss": 0.0096,
+      "step": 145
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.3451383709907532,
+      "learning_rate": 9.019828596704394e-05,
+      "loss": 0.0084,
+      "step": 150
+    },
+    {
+      "epoch": 15.533333333333333,
+      "grad_norm": 0.22912859916687012,
+      "learning_rate": 8.411418566661388e-05,
+      "loss": 0.0087,
+      "step": 155
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.2961307466030121,
+      "learning_rate": 7.808987598431303e-05,
+      "loss": 0.0054,
+      "step": 160
+    },
+    {
+      "epoch": 16.533333333333335,
+      "grad_norm": 0.05174371972680092,
+      "learning_rate": 7.21480310614947e-05,
+      "loss": 0.0037,
+      "step": 165
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.6668692827224731,
+      "learning_rate": 6.6311014660778e-05,
+      "loss": 0.0086,
+      "step": 170
+    },
+    {
+      "epoch": 17.533333333333335,
+      "grad_norm": 0.0423920676112175,
+      "learning_rate": 6.060079599389521e-05,
+      "loss": 0.0046,
+      "step": 175
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.048323437571525574,
+      "learning_rate": 5.503886703453933e-05,
+      "loss": 0.005,
+      "step": 180
+    },
+    {
+      "epoch": 18.533333333333335,
+      "grad_norm": 0.14866454899311066,
+      "learning_rate": 4.964616162742826e-05,
+      "loss": 0.0039,
+      "step": 185
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.04198712110519409,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0033,
+      "step": 190
+    },
+    {
+      "epoch": 19.533333333333335,
+      "grad_norm": 0.037916265428066254,
+      "learning_rate": 3.944889585956746e-05,
+      "loss": 0.0075,
+      "step": 195
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.031426794826984406,
+      "learning_rate": 3.468271570462235e-05,
+      "loss": 0.0036,
+      "step": 200
+    },
+    {
+      "epoch": 20.533333333333335,
+      "grad_norm": 0.1819785088300705,
+      "learning_rate": 3.016237505910272e-05,
+      "loss": 0.0062,
+      "step": 205
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 0.09462948143482208,
+      "learning_rate": 2.5904887464504114e-05,
+      "loss": 0.0034,
+      "step": 210
+    },
+    {
+      "epoch": 21.533333333333335,
+      "grad_norm": 0.11672957241535187,
+      "learning_rate": 2.1926277142790552e-05,
+      "loss": 0.0025,
+      "step": 215
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.04571106657385826,
+      "learning_rate": 1.824151868484164e-05,
+      "loss": 0.0042,
+      "step": 220
+    },
+    {
+      "epoch": 22.533333333333335,
+      "grad_norm": 0.019737839698791504,
+      "learning_rate": 1.486448068947348e-05,
+      "loss": 0.0021,
+      "step": 225
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.03002820909023285,
+      "learning_rate": 1.1807873565164506e-05,
+      "loss": 0.0049,
+      "step": 230
+    },
+    {
+      "epoch": 23.533333333333335,
+      "grad_norm": 0.24355602264404297,
+      "learning_rate": 9.083201690947763e-06,
+      "loss": 0.004,
+      "step": 235
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.035868410021066666,
+      "learning_rate": 6.700720116526116e-06,
+      "loss": 0.0024,
+      "step": 240
+    },
+    {
+      "epoch": 24.533333333333335,
+      "grad_norm": 0.029756512492895126,
+      "learning_rate": 4.669395964580614e-06,
+      "loss": 0.0025,
+      "step": 245
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.2836012542247772,
+      "learning_rate": 2.996874680545603e-06,
+      "loss": 0.0059,
+      "step": 250
+    },
+    {
+      "epoch": 25.533333333333335,
+      "grad_norm": 0.2209901213645935,
+      "learning_rate": 1.6894512568783716e-06,
+      "loss": 0.004,
+      "step": 255
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 0.023770242929458618,
+      "learning_rate": 7.520465401290033e-07,
+      "loss": 0.0033,
+      "step": 260
+    },
+    {
+      "epoch": 26.533333333333335,
+      "grad_norm": 0.02641889452934265,
+      "learning_rate": 1.8818870998508208e-07,
+      "loss": 0.0032,
+      "step": 265
+    },
+    {
+      "epoch": 27.0,
+      "grad_norm": 0.03176680952310562,
+      "learning_rate": 0.0,
+      "loss": 0.0025,
+      "step": 270
     },
     {
-      "epoch": 4.173913043478261,
-      "step": 50,
-      "total_flos": 2.8914967713060864e+16,
-      "train_loss": 0.6689150285720825,
-      "train_runtime": 536.5173,
-      "train_samples_per_second": 1.491,
-      "train_steps_per_second": 0.093
+      "epoch": 27.0,
+      "step": 270,
+      "total_flos": 1.3785203655910195e+17,
+      "train_loss": 0.12853161850599226,
+      "train_runtime": 2497.1205,
+      "train_samples_per_second": 1.802,
+      "train_steps_per_second": 0.108
     }
   ],
   "logging_steps": 5,
-  "max_steps": 50,
+  "max_steps": 270,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 30,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -146,7 +414,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8914967713060864e+16,
+  "total_flos": 1.3785203655910195e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b379700727532ab22acd204ba858eb7dbdb3c8a9496a4558aed006ad9fda0ad3
+oid sha256:2a98014c58d55a004fcf6f633921d0efe54b1543b60e7ac340ed1a1b1f40acb7
 size 5624