Training in progress, step 150, checkpoint

checkpoint-150/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3-mini-4k-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 0.11.1

checkpoint-150/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 512,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_up_proj",
+    "down_proj",
+    "o_proj",
+    "qkv_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc608678a741705f8a4798f2cd9a3b82a72922a390c56ed62e3e560bc6fa3ab9
+size 2004651224

checkpoint-150/added_tokens.json

@@ -0,0 +1,17 @@
+{
+  "</plan>": 32014,
+  "</thinking>": 32012,
+  "<plan>": 32013,
+  "<thinking>": 32011,
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c415aee541b544dd71a3fe66b371e9c9645d24b25f51be490afd9a0ee33551e
+size 4009448634

checkpoint-150/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54dc8a6e3fe14a41122aa8fa3190c54300056c70a27309ba399b9023bf344e8f
+size 15984

checkpoint-150/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da5e02fefd938f06090ad9332db3e38dbe95fb77dcd59c20b837ee7b4bc6b56
+size 15984

checkpoint-150/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a02efded1bea4dc84cea0eda463cddfce0c49815985b04b4f934098bd7be33
+size 15984

checkpoint-150/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e117f62e33df54b80a82f3d7ec47fbcbbd45db406e9ecfae128a75a5e5e2e33a
+size 15984

checkpoint-150/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8486aa224cb4dce1729cdb863b9213ef237f6775b502f65dc4b9a008a12c3631
+size 15984

checkpoint-150/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d14086cde94ce32a81094c4041c93d54107c414583c4f704bc3c7cb98438e2
+size 15984

checkpoint-150/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf079ec38d00894bebc63d0853018a10efeda0a3c5a60bd3e14654e1929f62e
+size 15984

checkpoint-150/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978974b2542a74e1b6d63c4e1a14f1e5343ee69cb5550e4113b8de32cbcaab04
+size 15984

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498aead13f6936fcdaeb826318751f2ed8774110c2f074b8c2e81673156ef38f
+size 1064

checkpoint-150/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-150/tokenizer.model

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

checkpoint-150/tokenizer_config.json

@@ -0,0 +1,163 @@
+{
+  "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
+    },
+    "32011": {
+      "content": "<thinking>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "</thinking>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<plan>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32014": {
+      "content": "</plan>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|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|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-150/trainer_state.json

@@ -0,0 +1,1115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5050505050505051,
+  "eval_steps": 38,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003367003367003367,
+      "grad_norm": 2.0,
+      "learning_rate": 2.2727272727272729e-07,
+      "loss": 1.0833,
+      "step": 1
+    },
+    {
+      "epoch": 0.003367003367003367,
+      "eval_loss": 1.032954454421997,
+      "eval_runtime": 8.7985,
+      "eval_samples_per_second": 56.828,
+      "eval_steps_per_second": 3.637,
+      "step": 1
+    },
+    {
+      "epoch": 0.006734006734006734,
+      "grad_norm": 2.265625,
+      "learning_rate": 4.5454545454545457e-07,
+      "loss": 0.996,
+      "step": 2
+    },
+    {
+      "epoch": 0.010101010101010102,
+      "grad_norm": 1.640625,
+      "learning_rate": 6.818181818181818e-07,
+      "loss": 1.0489,
+      "step": 3
+    },
+    {
+      "epoch": 0.013468013468013467,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 1.0546,
+      "step": 4
+    },
+    {
+      "epoch": 0.016835016835016835,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.1363636363636364e-06,
+      "loss": 1.0341,
+      "step": 5
+    },
+    {
+      "epoch": 0.020202020202020204,
+      "grad_norm": 1.9921875,
+      "learning_rate": 1.3636363636363636e-06,
+      "loss": 1.0136,
+      "step": 6
+    },
+    {
+      "epoch": 0.02356902356902357,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.590909090909091e-06,
+      "loss": 1.0305,
+      "step": 7
+    },
+    {
+      "epoch": 0.026936026936026935,
+      "grad_norm": 2.359375,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 1.0226,
+      "step": 8
+    },
+    {
+      "epoch": 0.030303030303030304,
+      "grad_norm": 2.3125,
+      "learning_rate": 2.0454545454545457e-06,
+      "loss": 1.0745,
+      "step": 9
+    },
+    {
+      "epoch": 0.03367003367003367,
+      "grad_norm": 2.359375,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 1.0232,
+      "step": 10
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": 2.53125,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0106,
+      "step": 11
+    },
+    {
+      "epoch": 0.04040404040404041,
+      "grad_norm": 2.125,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 1.0541,
+      "step": 12
+    },
+    {
+      "epoch": 0.04377104377104377,
+      "grad_norm": 2.15625,
+      "learning_rate": 2.954545454545455e-06,
+      "loss": 1.0693,
+      "step": 13
+    },
+    {
+      "epoch": 0.04713804713804714,
+      "grad_norm": 1.8359375,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 1.0338,
+      "step": 14
+    },
+    {
+      "epoch": 0.050505050505050504,
+      "grad_norm": 2.0,
+      "learning_rate": 3.409090909090909e-06,
+      "loss": 1.0464,
+      "step": 15
+    },
+    {
+      "epoch": 0.05387205387205387,
+      "grad_norm": 2.34375,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 1.0684,
+      "step": 16
+    },
+    {
+      "epoch": 0.05723905723905724,
+      "grad_norm": 1.8125,
+      "learning_rate": 3.863636363636364e-06,
+      "loss": 1.0117,
+      "step": 17
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 1.90625,
+      "learning_rate": 4.0909090909090915e-06,
+      "loss": 1.0138,
+      "step": 18
+    },
+    {
+      "epoch": 0.06397306397306397,
+      "grad_norm": 1.59375,
+      "learning_rate": 4.3181818181818185e-06,
+      "loss": 0.9873,
+      "step": 19
+    },
+    {
+      "epoch": 0.06734006734006734,
+      "grad_norm": 1.59375,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.0524,
+      "step": 20
+    },
+    {
+      "epoch": 0.0707070707070707,
+      "grad_norm": 1.3984375,
+      "learning_rate": 4.772727272727273e-06,
+      "loss": 1.0479,
+      "step": 21
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 1.609375,
+      "learning_rate": 5e-06,
+      "loss": 0.9894,
+      "step": 22
+    },
+    {
+      "epoch": 0.07744107744107744,
+      "grad_norm": 1.3671875,
+      "learning_rate": 5.2272727272727274e-06,
+      "loss": 0.983,
+      "step": 23
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 1.6328125,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 1.0563,
+      "step": 24
+    },
+    {
+      "epoch": 0.08417508417508418,
+      "grad_norm": 1.34375,
+      "learning_rate": 5.681818181818183e-06,
+      "loss": 0.9966,
+      "step": 25
+    },
+    {
+      "epoch": 0.08754208754208755,
+      "grad_norm": 1.25,
+      "learning_rate": 5.90909090909091e-06,
+      "loss": 0.9922,
+      "step": 26
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 1.3984375,
+      "learning_rate": 6.136363636363637e-06,
+      "loss": 1.0677,
+      "step": 27
+    },
+    {
+      "epoch": 0.09427609427609428,
+      "grad_norm": 1.3828125,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 1.0325,
+      "step": 28
+    },
+    {
+      "epoch": 0.09764309764309764,
+      "grad_norm": 1.1953125,
+      "learning_rate": 6.590909090909091e-06,
+      "loss": 1.0159,
+      "step": 29
+    },
+    {
+      "epoch": 0.10101010101010101,
+      "grad_norm": 1.3125,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 1.0384,
+      "step": 30
+    },
+    {
+      "epoch": 0.10437710437710437,
+      "grad_norm": 1.1171875,
+      "learning_rate": 7.045454545454546e-06,
+      "loss": 0.9949,
+      "step": 31
+    },
+    {
+      "epoch": 0.10774410774410774,
+      "grad_norm": 1.2421875,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 1.0284,
+      "step": 32
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 1.15625,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.0245,
+      "step": 33
+    },
+    {
+      "epoch": 0.11447811447811448,
+      "grad_norm": 1.1875,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 1.0103,
+      "step": 34
+    },
+    {
+      "epoch": 0.11784511784511785,
+      "grad_norm": 1.125,
+      "learning_rate": 7.954545454545455e-06,
+      "loss": 1.0129,
+      "step": 35
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 1.03125,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.965,
+      "step": 36
+    },
+    {
+      "epoch": 0.12457912457912458,
+      "grad_norm": 1.109375,
+      "learning_rate": 8.40909090909091e-06,
+      "loss": 1.0027,
+      "step": 37
+    },
+    {
+      "epoch": 0.12794612794612795,
+      "grad_norm": 1.0859375,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 1.0093,
+      "step": 38
+    },
+    {
+      "epoch": 0.12794612794612795,
+      "eval_loss": 0.9909602999687195,
+      "eval_runtime": 8.9064,
+      "eval_samples_per_second": 56.139,
+      "eval_steps_per_second": 3.593,
+      "step": 38
+    },
+    {
+      "epoch": 0.13131313131313133,
+      "grad_norm": 0.96484375,
+      "learning_rate": 8.863636363636365e-06,
+      "loss": 0.98,
+      "step": 39
+    },
+    {
+      "epoch": 0.13468013468013468,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.13804713804713806,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.318181818181819e-06,
+      "loss": 0.9658,
+      "step": 41
+    },
+    {
+      "epoch": 0.1414141414141414,
+      "grad_norm": 0.95703125,
+      "learning_rate": 9.545454545454547e-06,
+      "loss": 0.9656,
+      "step": 42
+    },
+    {
+      "epoch": 0.1447811447811448,
+      "grad_norm": 1.0,
+      "learning_rate": 9.772727272727273e-06,
+      "loss": 0.9528,
+      "step": 43
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1e-05,
+      "loss": 0.9546,
+      "step": 44
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 0.984375,
+      "learning_rate": 9.999965606811854e-06,
+      "loss": 0.9406,
+      "step": 45
+    },
+    {
+      "epoch": 0.15488215488215487,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.99986242772057e-06,
+      "loss": 0.9975,
+      "step": 46
+    },
+    {
+      "epoch": 0.15824915824915825,
+      "grad_norm": 0.94140625,
+      "learning_rate": 9.99969046414561e-06,
+      "loss": 0.9567,
+      "step": 47
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.96484375,
+      "learning_rate": 9.999449718452724e-06,
+      "loss": 0.9707,
+      "step": 48
+    },
+    {
+      "epoch": 0.16498316498316498,
+      "grad_norm": 1.0,
+      "learning_rate": 9.999140193953923e-06,
+      "loss": 0.9559,
+      "step": 49
+    },
+    {
+      "epoch": 0.16835016835016836,
+      "grad_norm": 0.99609375,
+      "learning_rate": 9.998761894907414e-06,
+      "loss": 0.9398,
+      "step": 50
+    },
+    {
+      "epoch": 0.1717171717171717,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.998314826517564e-06,
+      "loss": 0.9329,
+      "step": 51
+    },
+    {
+      "epoch": 0.1750841750841751,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.997798994934812e-06,
+      "loss": 0.9478,
+      "step": 52
+    },
+    {
+      "epoch": 0.17845117845117844,
+      "grad_norm": 0.94140625,
+      "learning_rate": 9.997214407255602e-06,
+      "loss": 0.9062,
+      "step": 53
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.996561071522264e-06,
+      "loss": 0.9089,
+      "step": 54
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.995838996722916e-06,
+      "loss": 0.9561,
+      "step": 55
+    },
+    {
+      "epoch": 0.18855218855218855,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.995048192791341e-06,
+      "loss": 0.8948,
+      "step": 56
+    },
+    {
+      "epoch": 0.1919191919191919,
+      "grad_norm": 0.91796875,
+      "learning_rate": 9.994188670606845e-06,
+      "loss": 0.9095,
+      "step": 57
+    },
+    {
+      "epoch": 0.19528619528619529,
+      "grad_norm": 0.8515625,
+      "learning_rate": 9.993260441994116e-06,
+      "loss": 0.9137,
+      "step": 58
+    },
+    {
+      "epoch": 0.19865319865319866,
+      "grad_norm": 0.8671875,
+      "learning_rate": 9.992263519723046e-06,
+      "loss": 0.9012,
+      "step": 59
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 0.8046875,
+      "learning_rate": 9.99119791750857e-06,
+      "loss": 0.9074,
+      "step": 60
+    },
+    {
+      "epoch": 0.2053872053872054,
+      "grad_norm": 1.0859375,
+      "learning_rate": 9.990063650010473e-06,
+      "loss": 0.9106,
+      "step": 61
+    },
+    {
+      "epoch": 0.20875420875420875,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.988860732833183e-06,
+      "loss": 0.9012,
+      "step": 62
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 0.93359375,
+      "learning_rate": 9.987589182525562e-06,
+      "loss": 0.8928,
+      "step": 63
+    },
+    {
+      "epoch": 0.21548821548821548,
+      "grad_norm": 0.921875,
+      "learning_rate": 9.98624901658068e-06,
+      "loss": 0.9487,
+      "step": 64
+    },
+    {
+      "epoch": 0.21885521885521886,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.984840253435569e-06,
+      "loss": 0.8887,
+      "step": 65
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.8671875,
+      "learning_rate": 9.983362912470967e-06,
+      "loss": 0.9152,
+      "step": 66
+    },
+    {
+      "epoch": 0.2255892255892256,
+      "grad_norm": 0.83984375,
+      "learning_rate": 9.981817014011066e-06,
+      "loss": 0.8849,
+      "step": 67
+    },
+    {
+      "epoch": 0.22895622895622897,
+      "grad_norm": 0.94921875,
+      "learning_rate": 9.980202579323212e-06,
+      "loss": 0.9386,
+      "step": 68
+    },
+    {
+      "epoch": 0.23232323232323232,
+      "grad_norm": 0.8203125,
+      "learning_rate": 9.978519630617632e-06,
+      "loss": 0.8651,
+      "step": 69
+    },
+    {
+      "epoch": 0.2356902356902357,
+      "grad_norm": 0.7109375,
+      "learning_rate": 9.976768191047109e-06,
+      "loss": 0.9044,
+      "step": 70
+    },
+    {
+      "epoch": 0.23905723905723905,
+      "grad_norm": 1.03125,
+      "learning_rate": 9.974948284706684e-06,
+      "loss": 0.8702,
+      "step": 71
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.91796875,
+      "learning_rate": 9.973059936633308e-06,
+      "loss": 0.8748,
+      "step": 72
+    },
+    {
+      "epoch": 0.24579124579124578,
+      "grad_norm": 0.66796875,
+      "learning_rate": 9.971103172805504e-06,
+      "loss": 0.8443,
+      "step": 73
+    },
+    {
+      "epoch": 0.24915824915824916,
+      "grad_norm": 0.671875,
+      "learning_rate": 9.969078020143013e-06,
+      "loss": 0.8605,
+      "step": 74
+    },
+    {
+      "epoch": 0.25252525252525254,
+      "grad_norm": 0.6796875,
+      "learning_rate": 9.966984506506415e-06,
+      "loss": 0.8661,
+      "step": 75
+    },
+    {
+      "epoch": 0.2558922558922559,
+      "grad_norm": 0.953125,
+      "learning_rate": 9.964822660696753e-06,
+      "loss": 0.9169,
+      "step": 76
+    },
+    {
+      "epoch": 0.2558922558922559,
+      "eval_loss": 0.8667835593223572,
+      "eval_runtime": 8.6819,
+      "eval_samples_per_second": 57.591,
+      "eval_steps_per_second": 3.686,
+      "step": 76
+    },
+    {
+      "epoch": 0.25925925925925924,
+      "grad_norm": 0.86328125,
+      "learning_rate": 9.96259251245514e-06,
+      "loss": 0.8719,
+      "step": 77
+    },
+    {
+      "epoch": 0.26262626262626265,
+      "grad_norm": 0.66796875,
+      "learning_rate": 9.960294092462332e-06,
+      "loss": 0.8438,
+      "step": 78
+    },
+    {
+      "epoch": 0.265993265993266,
+      "grad_norm": 0.66796875,
+      "learning_rate": 9.957927432338332e-06,
+      "loss": 0.8723,
+      "step": 79
+    },
+    {
+      "epoch": 0.26936026936026936,
+      "grad_norm": 1.3828125,
+      "learning_rate": 9.95549256464193e-06,
+      "loss": 0.8987,
+      "step": 80
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 0.69921875,
+      "learning_rate": 9.952989522870275e-06,
+      "loss": 0.8188,
+      "step": 81
+    },
+    {
+      "epoch": 0.2760942760942761,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.950418341458398e-06,
+      "loss": 0.8521,
+      "step": 82
+    },
+    {
+      "epoch": 0.27946127946127947,
+      "grad_norm": 0.828125,
+      "learning_rate": 9.947779055778752e-06,
+      "loss": 0.8305,
+      "step": 83
+    },
+    {
+      "epoch": 0.2828282828282828,
+      "grad_norm": 0.9453125,
+      "learning_rate": 9.945071702140716e-06,
+      "loss": 0.856,
+      "step": 84
+    },
+    {
+      "epoch": 0.28619528619528617,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.9422963177901e-06,
+      "loss": 0.8512,
+      "step": 85
+    },
+    {
+      "epoch": 0.2895622895622896,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.939452940908627e-06,
+      "loss": 0.818,
+      "step": 86
+    },
+    {
+      "epoch": 0.29292929292929293,
+      "grad_norm": 0.640625,
+      "learning_rate": 9.936541610613417e-06,
+      "loss": 0.8071,
+      "step": 87
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.82421875,
+      "learning_rate": 9.933562366956445e-06,
+      "loss": 0.8559,
+      "step": 88
+    },
+    {
+      "epoch": 0.2996632996632997,
+      "grad_norm": 1.046875,
+      "learning_rate": 9.930515250923985e-06,
+      "loss": 0.8646,
+      "step": 89
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 0.76953125,
+      "learning_rate": 9.927400304436048e-06,
+      "loss": 0.8179,
+      "step": 90
+    },
+    {
+      "epoch": 0.3063973063973064,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.924217570345814e-06,
+      "loss": 0.8093,
+      "step": 91
+    },
+    {
+      "epoch": 0.30976430976430974,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.920967092439028e-06,
+      "loss": 0.8073,
+      "step": 92
+    },
+    {
+      "epoch": 0.31313131313131315,
+      "grad_norm": 0.84375,
+      "learning_rate": 9.917648915433413e-06,
+      "loss": 0.9031,
+      "step": 93
+    },
+    {
+      "epoch": 0.3164983164983165,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.914263084978041e-06,
+      "loss": 0.8568,
+      "step": 94
+    },
+    {
+      "epoch": 0.31986531986531985,
+      "grad_norm": 0.8671875,
+      "learning_rate": 9.910809647652716e-06,
+      "loss": 0.7819,
+      "step": 95
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.84765625,
+      "learning_rate": 9.907288650967324e-06,
+      "loss": 0.8236,
+      "step": 96
+    },
+    {
+      "epoch": 0.3265993265993266,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.903700143361185e-06,
+      "loss": 0.8418,
+      "step": 97
+    },
+    {
+      "epoch": 0.32996632996632996,
+      "grad_norm": 0.94921875,
+      "learning_rate": 9.900044174202389e-06,
+      "loss": 0.8313,
+      "step": 98
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.8125,
+      "learning_rate": 9.896320793787106e-06,
+      "loss": 0.8158,
+      "step": 99
+    },
+    {
+      "epoch": 0.3367003367003367,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.892530053338909e-06,
+      "loss": 0.7956,
+      "step": 100
+    },
+    {
+      "epoch": 0.3400673400673401,
+      "grad_norm": 0.94921875,
+      "learning_rate": 9.888672005008054e-06,
+      "loss": 0.8154,
+      "step": 101
+    },
+    {
+      "epoch": 0.3434343434343434,
+      "grad_norm": 0.6328125,
+      "learning_rate": 9.884746701870778e-06,
+      "loss": 0.8322,
+      "step": 102
+    },
+    {
+      "epoch": 0.3468013468013468,
+      "grad_norm": 0.62890625,
+      "learning_rate": 9.880754197928553e-06,
+      "loss": 0.8133,
+      "step": 103
+    },
+    {
+      "epoch": 0.3501683501683502,
+      "grad_norm": 0.76953125,
+      "learning_rate": 9.876694548107358e-06,
+      "loss": 0.7882,
+      "step": 104
+    },
+    {
+      "epoch": 0.35353535353535354,
+      "grad_norm": 1.03125,
+      "learning_rate": 9.87256780825691e-06,
+      "loss": 0.8264,
+      "step": 105
+    },
+    {
+      "epoch": 0.3569023569023569,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.868374035149906e-06,
+      "loss": 0.7894,
+      "step": 106
+    },
+    {
+      "epoch": 0.3602693602693603,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.864113286481237e-06,
+      "loss": 0.7807,
+      "step": 107
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.859785620867197e-06,
+      "loss": 0.7895,
+      "step": 108
+    },
+    {
+      "epoch": 0.367003367003367,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.855391097844671e-06,
+      "loss": 0.7936,
+      "step": 109
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.8984375,
+      "learning_rate": 9.850929777870324e-06,
+      "loss": 0.8024,
+      "step": 110
+    },
+    {
+      "epoch": 0.37373737373737376,
+      "grad_norm": 0.6640625,
+      "learning_rate": 9.846401722319759e-06,
+      "loss": 0.7542,
+      "step": 111
+    },
+    {
+      "epoch": 0.3771043771043771,
+      "grad_norm": 1.1640625,
+      "learning_rate": 9.841806993486686e-06,
+      "loss": 0.7689,
+      "step": 112
+    },
+    {
+      "epoch": 0.38047138047138046,
+      "grad_norm": 0.765625,
+      "learning_rate": 9.837145654582055e-06,
+      "loss": 0.7133,
+      "step": 113
+    },
+    {
+      "epoch": 0.3838383838383838,
+      "grad_norm": 0.87109375,
+      "learning_rate": 9.832417769733185e-06,
+      "loss": 0.795,
+      "step": 114
+    },
+    {
+      "epoch": 0.3838383838383838,
+      "eval_loss": 0.7676474452018738,
+      "eval_runtime": 8.7789,
+      "eval_samples_per_second": 56.955,
+      "eval_steps_per_second": 3.645,
+      "step": 114
+    },
+    {
+      "epoch": 0.3872053872053872,
+      "grad_norm": 0.86328125,
+      "learning_rate": 9.827623403982893e-06,
+      "loss": 0.7992,
+      "step": 115
+    },
+    {
+      "epoch": 0.39057239057239057,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.822762623288584e-06,
+      "loss": 0.7678,
+      "step": 116
+    },
+    {
+      "epoch": 0.3939393939393939,
+      "grad_norm": 0.85546875,
+      "learning_rate": 9.81783549452136e-06,
+      "loss": 0.7861,
+      "step": 117
+    },
+    {
+      "epoch": 0.39730639730639733,
+      "grad_norm": 0.71484375,
+      "learning_rate": 9.812842085465086e-06,
+      "loss": 0.7447,
+      "step": 118
+    },
+    {
+      "epoch": 0.4006734006734007,
+      "grad_norm": 0.5703125,
+      "learning_rate": 9.807782464815463e-06,
+      "loss": 0.7218,
+      "step": 119
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.802656702179088e-06,
+      "loss": 0.7637,
+      "step": 120
+    },
+    {
+      "epoch": 0.4074074074074074,
+      "grad_norm": 0.54296875,
+      "learning_rate": 9.797464868072489e-06,
+      "loss": 0.7588,
+      "step": 121
+    },
+    {
+      "epoch": 0.4107744107744108,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.792207033921152e-06,
+      "loss": 0.7539,
+      "step": 122
+    },
+    {
+      "epoch": 0.41414141414141414,
+      "grad_norm": 0.8046875,
+      "learning_rate": 9.786883272058554e-06,
+      "loss": 0.7524,
+      "step": 123
+    },
+    {
+      "epoch": 0.4175084175084175,
+      "grad_norm": 0.6953125,
+      "learning_rate": 9.781493655725149e-06,
+      "loss": 0.731,
+      "step": 124
+    },
+    {
+      "epoch": 0.4208754208754209,
+      "grad_norm": 0.64453125,
+      "learning_rate": 9.776038259067375e-06,
+      "loss": 0.8022,
+      "step": 125
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 0.48046875,
+      "learning_rate": 9.770517157136625e-06,
+      "loss": 0.7528,
+      "step": 126
+    },
+    {
+      "epoch": 0.4276094276094276,
+      "grad_norm": 0.5546875,
+      "learning_rate": 9.764930425888216e-06,
+      "loss": 0.7037,
+      "step": 127
+    },
+    {
+      "epoch": 0.43097643097643096,
+      "grad_norm": 0.546875,
+      "learning_rate": 9.759278142180348e-06,
+      "loss": 0.7519,
+      "step": 128
+    },
+    {
+      "epoch": 0.43434343434343436,
+      "grad_norm": 0.61328125,
+      "learning_rate": 9.753560383773046e-06,
+      "loss": 0.8163,
+      "step": 129
+    },
+    {
+      "epoch": 0.4377104377104377,
+      "grad_norm": 0.53125,
+      "learning_rate": 9.747777229327085e-06,
+      "loss": 0.7292,
+      "step": 130
+    },
+    {
+      "epoch": 0.44107744107744107,
+      "grad_norm": 0.58203125,
+      "learning_rate": 9.741928758402912e-06,
+      "loss": 0.7351,
+      "step": 131
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.5234375,
+      "learning_rate": 9.736015051459551e-06,
+      "loss": 0.7429,
+      "step": 132
+    },
+    {
+      "epoch": 0.4478114478114478,
+      "grad_norm": 0.65234375,
+      "learning_rate": 9.730036189853497e-06,
+      "loss": 0.7616,
+      "step": 133
+    },
+    {
+      "epoch": 0.4511784511784512,
+      "grad_norm": 0.53125,
+      "learning_rate": 9.723992255837596e-06,
+      "loss": 0.7263,
+      "step": 134
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.5546875,
+      "learning_rate": 9.717883332559911e-06,
+      "loss": 0.7427,
+      "step": 135
+    },
+    {
+      "epoch": 0.45791245791245794,
+      "grad_norm": 0.66796875,
+      "learning_rate": 9.71170950406258e-06,
+      "loss": 0.7261,
+      "step": 136
+    },
+    {
+      "epoch": 0.4612794612794613,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.705470855280661e-06,
+      "loss": 0.754,
+      "step": 137
+    },
+    {
+      "epoch": 0.46464646464646464,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.699167472040965e-06,
+      "loss": 0.7554,
+      "step": 138
+    },
+    {
+      "epoch": 0.468013468013468,
+      "grad_norm": 0.5546875,
+      "learning_rate": 9.692799441060868e-06,
+      "loss": 0.7488,
+      "step": 139
+    },
+    {
+      "epoch": 0.4713804713804714,
+      "grad_norm": 0.53125,
+      "learning_rate": 9.686366849947126e-06,
+      "loss": 0.7066,
+      "step": 140
+    },
+    {
+      "epoch": 0.47474747474747475,
+      "grad_norm": 0.55078125,
+      "learning_rate": 9.679869787194664e-06,
+      "loss": 0.7818,
+      "step": 141
+    },
+    {
+      "epoch": 0.4781144781144781,
+      "grad_norm": 0.4765625,
+      "learning_rate": 9.673308342185366e-06,
+      "loss": 0.7289,
+      "step": 142
+    },
+    {
+      "epoch": 0.48148148148148145,
+      "grad_norm": 0.62109375,
+      "learning_rate": 9.666682605186834e-06,
+      "loss": 0.7301,
+      "step": 143
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.54296875,
+      "learning_rate": 9.659992667351157e-06,
+      "loss": 0.7673,
+      "step": 144
+    },
+    {
+      "epoch": 0.4882154882154882,
+      "grad_norm": 0.486328125,
+      "learning_rate": 9.653238620713652e-06,
+      "loss": 0.6884,
+      "step": 145
+    },
+    {
+      "epoch": 0.49158249158249157,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.646420558191596e-06,
+      "loss": 0.7043,
+      "step": 146
+    },
+    {
+      "epoch": 0.494949494949495,
+      "grad_norm": 0.51171875,
+      "learning_rate": 9.639538573582952e-06,
+      "loss": 0.7122,
+      "step": 147
+    },
+    {
+      "epoch": 0.4983164983164983,
+      "grad_norm": 0.498046875,
+      "learning_rate": 9.632592761565078e-06,
+      "loss": 0.7232,
+      "step": 148
+    },
+    {
+      "epoch": 0.5016835016835017,
+      "grad_norm": 0.5625,
+      "learning_rate": 9.625583217693419e-06,
+      "loss": 0.7311,
+      "step": 149
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.618510038400203e-06,
+      "loss": 0.7322,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 891,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 75,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.72875344887808e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67281bdc6cc564e812aa4cb73613aaae3277625d9bdb71d00a737b9619706f71
+size 6328