Training in progress, step 1000, checkpoint

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-7B-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-1000/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-7B-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": [
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ec04bc07d31457f281025585057d3f324c0fb9054ea7bb04bd8430e009b33a
+size 161533192

checkpoint-1000/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d943c6e3b45f3dbb4dfa25c9af44c957d4fea01d265d6268bdfbe8eed468c8
+size 323290986

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ed6fbe903f0b727bc7f9b8f326ac89d88fee0ce2cb8d61ca73fc58fb586587
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add37ff6723a967c488141c119bce3926696eb9434fcc64f559de00b0ff15632
+size 1064

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79faeb53ce66e372f424aa1072c822bd68c71927fb82a2c639b8120026616df5
+size 11418364

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,893 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0604453870625663,
+  "eval_steps": 50,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010604453870625663,
+      "grad_norm": 2.0663416385650635,
+      "learning_rate": 4.982325910215624e-05,
+      "loss": 1.91,
+      "step": 10
+    },
+    {
+      "epoch": 0.021208907741251327,
+      "grad_norm": 0.7459995746612549,
+      "learning_rate": 4.964651820431248e-05,
+      "loss": 1.0094,
+      "step": 20
+    },
+    {
+      "epoch": 0.031813361611876985,
+      "grad_norm": 0.656954824924469,
+      "learning_rate": 4.946977730646872e-05,
+      "loss": 0.8052,
+      "step": 30
+    },
+    {
+      "epoch": 0.042417815482502653,
+      "grad_norm": 0.7273707389831543,
+      "learning_rate": 4.929303640862496e-05,
+      "loss": 0.7145,
+      "step": 40
+    },
+    {
+      "epoch": 0.053022269353128315,
+      "grad_norm": 0.6689164042472839,
+      "learning_rate": 4.91162955107812e-05,
+      "loss": 0.6797,
+      "step": 50
+    },
+    {
+      "epoch": 0.053022269353128315,
+      "eval_loss": 0.8142186403274536,
+      "eval_runtime": 11.794,
+      "eval_samples_per_second": 40.699,
+      "eval_steps_per_second": 2.544,
+      "step": 50
+    },
+    {
+      "epoch": 0.06362672322375397,
+      "grad_norm": 0.6781293749809265,
+      "learning_rate": 4.893955461293744e-05,
+      "loss": 0.6249,
+      "step": 60
+    },
+    {
+      "epoch": 0.07423117709437964,
+      "grad_norm": 0.6776543259620667,
+      "learning_rate": 4.876281371509368e-05,
+      "loss": 0.612,
+      "step": 70
+    },
+    {
+      "epoch": 0.08483563096500531,
+      "grad_norm": 0.7603946924209595,
+      "learning_rate": 4.858607281724991e-05,
+      "loss": 0.5998,
+      "step": 80
+    },
+    {
+      "epoch": 0.09544008483563096,
+      "grad_norm": 0.7581377029418945,
+      "learning_rate": 4.8409331919406155e-05,
+      "loss": 0.6032,
+      "step": 90
+    },
+    {
+      "epoch": 0.10604453870625663,
+      "grad_norm": 0.7402133345603943,
+      "learning_rate": 4.823259102156239e-05,
+      "loss": 0.5912,
+      "step": 100
+    },
+    {
+      "epoch": 0.10604453870625663,
+      "eval_loss": 0.7294260859489441,
+      "eval_runtime": 11.8272,
+      "eval_samples_per_second": 40.585,
+      "eval_steps_per_second": 2.537,
+      "step": 100
+    },
+    {
+      "epoch": 0.11664899257688228,
+      "grad_norm": 0.8224169015884399,
+      "learning_rate": 4.8055850123718633e-05,
+      "loss": 0.578,
+      "step": 110
+    },
+    {
+      "epoch": 0.12725344644750794,
+      "grad_norm": 0.7843881249427795,
+      "learning_rate": 4.7879109225874866e-05,
+      "loss": 0.5751,
+      "step": 120
+    },
+    {
+      "epoch": 0.1378579003181336,
+      "grad_norm": 0.772152304649353,
+      "learning_rate": 4.770236832803111e-05,
+      "loss": 0.5471,
+      "step": 130
+    },
+    {
+      "epoch": 0.14846235418875928,
+      "grad_norm": 0.6972452998161316,
+      "learning_rate": 4.7525627430187344e-05,
+      "loss": 0.5516,
+      "step": 140
+    },
+    {
+      "epoch": 0.15906680805938495,
+      "grad_norm": 0.7806265354156494,
+      "learning_rate": 4.734888653234359e-05,
+      "loss": 0.5263,
+      "step": 150
+    },
+    {
+      "epoch": 0.15906680805938495,
+      "eval_loss": 0.6928939819335938,
+      "eval_runtime": 11.8093,
+      "eval_samples_per_second": 40.646,
+      "eval_steps_per_second": 2.54,
+      "step": 150
+    },
+    {
+      "epoch": 0.16967126193001061,
+      "grad_norm": 0.7372023463249207,
+      "learning_rate": 4.717214563449982e-05,
+      "loss": 0.5715,
+      "step": 160
+    },
+    {
+      "epoch": 0.18027571580063625,
+      "grad_norm": 0.8236038684844971,
+      "learning_rate": 4.699540473665606e-05,
+      "loss": 0.4987,
+      "step": 170
+    },
+    {
+      "epoch": 0.19088016967126192,
+      "grad_norm": 0.8057310581207275,
+      "learning_rate": 4.681866383881231e-05,
+      "loss": 0.5097,
+      "step": 180
+    },
+    {
+      "epoch": 0.2014846235418876,
+      "grad_norm": 0.7124797105789185,
+      "learning_rate": 4.664192294096854e-05,
+      "loss": 0.4952,
+      "step": 190
+    },
+    {
+      "epoch": 0.21208907741251326,
+      "grad_norm": 0.7755710482597351,
+      "learning_rate": 4.6465182043124786e-05,
+      "loss": 0.497,
+      "step": 200
+    },
+    {
+      "epoch": 0.21208907741251326,
+      "eval_loss": 0.6748186349868774,
+      "eval_runtime": 11.8077,
+      "eval_samples_per_second": 40.651,
+      "eval_steps_per_second": 2.541,
+      "step": 200
+    },
+    {
+      "epoch": 0.22269353128313893,
+      "grad_norm": 0.912337064743042,
+      "learning_rate": 4.628844114528102e-05,
+      "loss": 0.4997,
+      "step": 210
+    },
+    {
+      "epoch": 0.23329798515376457,
+      "grad_norm": 0.771654486656189,
+      "learning_rate": 4.6111700247437265e-05,
+      "loss": 0.5027,
+      "step": 220
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 0.8241815567016602,
+      "learning_rate": 4.59349593495935e-05,
+      "loss": 0.5196,
+      "step": 230
+    },
+    {
+      "epoch": 0.2545068928950159,
+      "grad_norm": 0.7876004576683044,
+      "learning_rate": 4.5758218451749736e-05,
+      "loss": 0.4791,
+      "step": 240
+    },
+    {
+      "epoch": 0.2651113467656416,
+      "grad_norm": 0.7941911816596985,
+      "learning_rate": 4.5581477553905975e-05,
+      "loss": 0.5078,
+      "step": 250
+    },
+    {
+      "epoch": 0.2651113467656416,
+      "eval_loss": 0.653518795967102,
+      "eval_runtime": 11.7906,
+      "eval_samples_per_second": 40.71,
+      "eval_steps_per_second": 2.544,
+      "step": 250
+    },
+    {
+      "epoch": 0.2757158006362672,
+      "grad_norm": 0.8866105079650879,
+      "learning_rate": 4.5404736656062215e-05,
+      "loss": 0.477,
+      "step": 260
+    },
+    {
+      "epoch": 0.2863202545068929,
+      "grad_norm": 0.8498968482017517,
+      "learning_rate": 4.5227995758218454e-05,
+      "loss": 0.4926,
+      "step": 270
+    },
+    {
+      "epoch": 0.29692470837751855,
+      "grad_norm": 0.8863232135772705,
+      "learning_rate": 4.505125486037469e-05,
+      "loss": 0.463,
+      "step": 280
+    },
+    {
+      "epoch": 0.3075291622481442,
+      "grad_norm": 0.9501034021377563,
+      "learning_rate": 4.487451396253093e-05,
+      "loss": 0.4809,
+      "step": 290
+    },
+    {
+      "epoch": 0.3181336161187699,
+      "grad_norm": 0.7933001518249512,
+      "learning_rate": 4.469777306468717e-05,
+      "loss": 0.4941,
+      "step": 300
+    },
+    {
+      "epoch": 0.3181336161187699,
+      "eval_loss": 0.6434358954429626,
+      "eval_runtime": 11.7969,
+      "eval_samples_per_second": 40.689,
+      "eval_steps_per_second": 2.543,
+      "step": 300
+    },
+    {
+      "epoch": 0.32873806998939553,
+      "grad_norm": 0.9145284295082092,
+      "learning_rate": 4.452103216684341e-05,
+      "loss": 0.5235,
+      "step": 310
+    },
+    {
+      "epoch": 0.33934252386002123,
+      "grad_norm": 0.8557764887809753,
+      "learning_rate": 4.434429126899965e-05,
+      "loss": 0.4809,
+      "step": 320
+    },
+    {
+      "epoch": 0.34994697773064687,
+      "grad_norm": 0.8337067365646362,
+      "learning_rate": 4.416755037115589e-05,
+      "loss": 0.4764,
+      "step": 330
+    },
+    {
+      "epoch": 0.3605514316012725,
+      "grad_norm": 0.8928807377815247,
+      "learning_rate": 4.399080947331213e-05,
+      "loss": 0.4634,
+      "step": 340
+    },
+    {
+      "epoch": 0.3711558854718982,
+      "grad_norm": 0.7639658451080322,
+      "learning_rate": 4.381406857546837e-05,
+      "loss": 0.4829,
+      "step": 350
+    },
+    {
+      "epoch": 0.3711558854718982,
+      "eval_loss": 0.6269502639770508,
+      "eval_runtime": 11.7838,
+      "eval_samples_per_second": 40.734,
+      "eval_steps_per_second": 2.546,
+      "step": 350
+    },
+    {
+      "epoch": 0.38176033934252385,
+      "grad_norm": 0.8374601006507874,
+      "learning_rate": 4.3637327677624606e-05,
+      "loss": 0.471,
+      "step": 360
+    },
+    {
+      "epoch": 0.39236479321314954,
+      "grad_norm": 0.9471817016601562,
+      "learning_rate": 4.3460586779780846e-05,
+      "loss": 0.4528,
+      "step": 370
+    },
+    {
+      "epoch": 0.4029692470837752,
+      "grad_norm": 0.8860051035881042,
+      "learning_rate": 4.328384588193708e-05,
+      "loss": 0.4684,
+      "step": 380
+    },
+    {
+      "epoch": 0.4135737009544008,
+      "grad_norm": 0.9099433422088623,
+      "learning_rate": 4.3107104984093324e-05,
+      "loss": 0.4294,
+      "step": 390
+    },
+    {
+      "epoch": 0.4241781548250265,
+      "grad_norm": 0.792826771736145,
+      "learning_rate": 4.2930364086249556e-05,
+      "loss": 0.4597,
+      "step": 400
+    },
+    {
+      "epoch": 0.4241781548250265,
+      "eval_loss": 0.6197967529296875,
+      "eval_runtime": 11.8062,
+      "eval_samples_per_second": 40.657,
+      "eval_steps_per_second": 2.541,
+      "step": 400
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.8295171856880188,
+      "learning_rate": 4.27536231884058e-05,
+      "loss": 0.4842,
+      "step": 410
+    },
+    {
+      "epoch": 0.44538706256627786,
+      "grad_norm": 0.9126204252243042,
+      "learning_rate": 4.2576882290562035e-05,
+      "loss": 0.4688,
+      "step": 420
+    },
+    {
+      "epoch": 0.4559915164369035,
+      "grad_norm": 0.9485805630683899,
+      "learning_rate": 4.240014139271828e-05,
+      "loss": 0.4803,
+      "step": 430
+    },
+    {
+      "epoch": 0.46659597030752914,
+      "grad_norm": 0.8756628036499023,
+      "learning_rate": 4.222340049487451e-05,
+      "loss": 0.4572,
+      "step": 440
+    },
+    {
+      "epoch": 0.47720042417815484,
+      "grad_norm": 0.907244086265564,
+      "learning_rate": 4.204665959703076e-05,
+      "loss": 0.4394,
+      "step": 450
+    },
+    {
+      "epoch": 0.47720042417815484,
+      "eval_loss": 0.6146622896194458,
+      "eval_runtime": 11.8005,
+      "eval_samples_per_second": 40.676,
+      "eval_steps_per_second": 2.542,
+      "step": 450
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.9201627969741821,
+      "learning_rate": 4.186991869918699e-05,
+      "loss": 0.4294,
+      "step": 460
+    },
+    {
+      "epoch": 0.4984093319194062,
+      "grad_norm": 0.9242031574249268,
+      "learning_rate": 4.169317780134323e-05,
+      "loss": 0.4335,
+      "step": 470
+    },
+    {
+      "epoch": 0.5090137857900318,
+      "grad_norm": 0.840977132320404,
+      "learning_rate": 4.151643690349947e-05,
+      "loss": 0.4639,
+      "step": 480
+    },
+    {
+      "epoch": 0.5196182396606575,
+      "grad_norm": 0.9487953782081604,
+      "learning_rate": 4.133969600565571e-05,
+      "loss": 0.4173,
+      "step": 490
+    },
+    {
+      "epoch": 0.5302226935312832,
+      "grad_norm": 0.8343156576156616,
+      "learning_rate": 4.116295510781195e-05,
+      "loss": 0.4647,
+      "step": 500
+    },
+    {
+      "epoch": 0.5302226935312832,
+      "eval_loss": 0.6104319095611572,
+      "eval_runtime": 11.8139,
+      "eval_samples_per_second": 40.63,
+      "eval_steps_per_second": 2.539,
+      "step": 500
+    },
+    {
+      "epoch": 0.5408271474019088,
+      "grad_norm": 0.9216362237930298,
+      "learning_rate": 4.098621420996819e-05,
+      "loss": 0.4499,
+      "step": 510
+    },
+    {
+      "epoch": 0.5514316012725344,
+      "grad_norm": 0.957593560218811,
+      "learning_rate": 4.080947331212443e-05,
+      "loss": 0.4202,
+      "step": 520
+    },
+    {
+      "epoch": 0.5620360551431601,
+      "grad_norm": 1.0103106498718262,
+      "learning_rate": 4.0632732414280666e-05,
+      "loss": 0.4315,
+      "step": 530
+    },
+    {
+      "epoch": 0.5726405090137858,
+      "grad_norm": 1.0909500122070312,
+      "learning_rate": 4.0455991516436905e-05,
+      "loss": 0.4476,
+      "step": 540
+    },
+    {
+      "epoch": 0.5832449628844114,
+      "grad_norm": 0.8890084028244019,
+      "learning_rate": 4.0279250618593144e-05,
+      "loss": 0.4408,
+      "step": 550
+    },
+    {
+      "epoch": 0.5832449628844114,
+      "eval_loss": 0.6050440073013306,
+      "eval_runtime": 11.7965,
+      "eval_samples_per_second": 40.69,
+      "eval_steps_per_second": 2.543,
+      "step": 550
+    },
+    {
+      "epoch": 0.5938494167550371,
+      "grad_norm": 1.038818359375,
+      "learning_rate": 4.0102509720749383e-05,
+      "loss": 0.4529,
+      "step": 560
+    },
+    {
+      "epoch": 0.6044538706256628,
+      "grad_norm": 1.0575263500213623,
+      "learning_rate": 3.992576882290562e-05,
+      "loss": 0.4409,
+      "step": 570
+    },
+    {
+      "epoch": 0.6150583244962884,
+      "grad_norm": 0.9827993512153625,
+      "learning_rate": 3.974902792506186e-05,
+      "loss": 0.4132,
+      "step": 580
+    },
+    {
+      "epoch": 0.6256627783669141,
+      "grad_norm": 0.9469496011734009,
+      "learning_rate": 3.95722870272181e-05,
+      "loss": 0.4075,
+      "step": 590
+    },
+    {
+      "epoch": 0.6362672322375398,
+      "grad_norm": 0.9693032503128052,
+      "learning_rate": 3.939554612937434e-05,
+      "loss": 0.4533,
+      "step": 600
+    },
+    {
+      "epoch": 0.6362672322375398,
+      "eval_loss": 0.5991437435150146,
+      "eval_runtime": 11.8081,
+      "eval_samples_per_second": 40.65,
+      "eval_steps_per_second": 2.541,
+      "step": 600
+    },
+    {
+      "epoch": 0.6468716861081655,
+      "grad_norm": 0.9771609306335449,
+      "learning_rate": 3.921880523153057e-05,
+      "loss": 0.4275,
+      "step": 610
+    },
+    {
+      "epoch": 0.6574761399787911,
+      "grad_norm": 0.9394034743309021,
+      "learning_rate": 3.904206433368682e-05,
+      "loss": 0.4066,
+      "step": 620
+    },
+    {
+      "epoch": 0.6680805938494168,
+      "grad_norm": 0.885517954826355,
+      "learning_rate": 3.886532343584305e-05,
+      "loss": 0.4071,
+      "step": 630
+    },
+    {
+      "epoch": 0.6786850477200425,
+      "grad_norm": 0.9775238633155823,
+      "learning_rate": 3.86885825379993e-05,
+      "loss": 0.4234,
+      "step": 640
+    },
+    {
+      "epoch": 0.689289501590668,
+      "grad_norm": 0.9256358742713928,
+      "learning_rate": 3.851184164015553e-05,
+      "loss": 0.4186,
+      "step": 650
+    },
+    {
+      "epoch": 0.689289501590668,
+      "eval_loss": 0.5974680781364441,
+      "eval_runtime": 11.8062,
+      "eval_samples_per_second": 40.657,
+      "eval_steps_per_second": 2.541,
+      "step": 650
+    },
+    {
+      "epoch": 0.6998939554612937,
+      "grad_norm": 0.9220837354660034,
+      "learning_rate": 3.8335100742311775e-05,
+      "loss": 0.4264,
+      "step": 660
+    },
+    {
+      "epoch": 0.7104984093319194,
+      "grad_norm": 1.0769790410995483,
+      "learning_rate": 3.8158359844468015e-05,
+      "loss": 0.4166,
+      "step": 670
+    },
+    {
+      "epoch": 0.721102863202545,
+      "grad_norm": 0.9368733763694763,
+      "learning_rate": 3.7981618946624254e-05,
+      "loss": 0.4296,
+      "step": 680
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 1.0023365020751953,
+      "learning_rate": 3.780487804878049e-05,
+      "loss": 0.4534,
+      "step": 690
+    },
+    {
+      "epoch": 0.7423117709437964,
+      "grad_norm": 1.062111258506775,
+      "learning_rate": 3.7628137150936725e-05,
+      "loss": 0.4378,
+      "step": 700
+    },
+    {
+      "epoch": 0.7423117709437964,
+      "eval_loss": 0.5889919400215149,
+      "eval_runtime": 11.8116,
+      "eval_samples_per_second": 40.638,
+      "eval_steps_per_second": 2.54,
+      "step": 700
+    },
+    {
+      "epoch": 0.7529162248144221,
+      "grad_norm": 1.0798842906951904,
+      "learning_rate": 3.745139625309297e-05,
+      "loss": 0.4168,
+      "step": 710
+    },
+    {
+      "epoch": 0.7635206786850477,
+      "grad_norm": 1.0573209524154663,
+      "learning_rate": 3.7274655355249204e-05,
+      "loss": 0.4244,
+      "step": 720
+    },
+    {
+      "epoch": 0.7741251325556734,
+      "grad_norm": 0.9914817810058594,
+      "learning_rate": 3.709791445740545e-05,
+      "loss": 0.4332,
+      "step": 730
+    },
+    {
+      "epoch": 0.7847295864262991,
+      "grad_norm": 1.0201358795166016,
+      "learning_rate": 3.692117355956168e-05,
+      "loss": 0.4225,
+      "step": 740
+    },
+    {
+      "epoch": 0.7953340402969247,
+      "grad_norm": 1.011526346206665,
+      "learning_rate": 3.674443266171793e-05,
+      "loss": 0.4069,
+      "step": 750
+    },
+    {
+      "epoch": 0.7953340402969247,
+      "eval_loss": 0.5948487520217896,
+      "eval_runtime": 11.8194,
+      "eval_samples_per_second": 40.611,
+      "eval_steps_per_second": 2.538,
+      "step": 750
+    },
+    {
+      "epoch": 0.8059384941675504,
+      "grad_norm": 0.9645175933837891,
+      "learning_rate": 3.656769176387416e-05,
+      "loss": 0.3833,
+      "step": 760
+    },
+    {
+      "epoch": 0.8165429480381761,
+      "grad_norm": 0.9826123118400574,
+      "learning_rate": 3.63909508660304e-05,
+      "loss": 0.4019,
+      "step": 770
+    },
+    {
+      "epoch": 0.8271474019088016,
+      "grad_norm": 0.957275927066803,
+      "learning_rate": 3.621420996818664e-05,
+      "loss": 0.4083,
+      "step": 780
+    },
+    {
+      "epoch": 0.8377518557794273,
+      "grad_norm": 1.0057812929153442,
+      "learning_rate": 3.603746907034288e-05,
+      "loss": 0.4218,
+      "step": 790
+    },
+    {
+      "epoch": 0.848356309650053,
+      "grad_norm": 1.0474872589111328,
+      "learning_rate": 3.586072817249912e-05,
+      "loss": 0.4224,
+      "step": 800
+    },
+    {
+      "epoch": 0.848356309650053,
+      "eval_loss": 0.5902166962623596,
+      "eval_runtime": 11.8122,
+      "eval_samples_per_second": 40.636,
+      "eval_steps_per_second": 2.54,
+      "step": 800
+    },
+    {
+      "epoch": 0.8589607635206787,
+      "grad_norm": 1.1121183633804321,
+      "learning_rate": 3.5683987274655356e-05,
+      "loss": 0.4035,
+      "step": 810
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 1.078808069229126,
+      "learning_rate": 3.5507246376811596e-05,
+      "loss": 0.3987,
+      "step": 820
+    },
+    {
+      "epoch": 0.88016967126193,
+      "grad_norm": 0.9879220724105835,
+      "learning_rate": 3.5330505478967835e-05,
+      "loss": 0.4107,
+      "step": 830
+    },
+    {
+      "epoch": 0.8907741251325557,
+      "grad_norm": 1.0545059442520142,
+      "learning_rate": 3.5153764581124074e-05,
+      "loss": 0.412,
+      "step": 840
+    },
+    {
+      "epoch": 0.9013785790031813,
+      "grad_norm": 1.0051729679107666,
+      "learning_rate": 3.497702368328031e-05,
+      "loss": 0.3962,
+      "step": 850
+    },
+    {
+      "epoch": 0.9013785790031813,
+      "eval_loss": 0.586068868637085,
+      "eval_runtime": 11.7963,
+      "eval_samples_per_second": 40.691,
+      "eval_steps_per_second": 2.543,
+      "step": 850
+    },
+    {
+      "epoch": 0.911983032873807,
+      "grad_norm": 1.0309350490570068,
+      "learning_rate": 3.480028278543655e-05,
+      "loss": 0.405,
+      "step": 860
+    },
+    {
+      "epoch": 0.9225874867444327,
+      "grad_norm": 1.063778281211853,
+      "learning_rate": 3.462354188759279e-05,
+      "loss": 0.4034,
+      "step": 870
+    },
+    {
+      "epoch": 0.9331919406150583,
+      "grad_norm": 1.0570268630981445,
+      "learning_rate": 3.444680098974903e-05,
+      "loss": 0.4038,
+      "step": 880
+    },
+    {
+      "epoch": 0.943796394485684,
+      "grad_norm": 1.0920844078063965,
+      "learning_rate": 3.427006009190527e-05,
+      "loss": 0.3996,
+      "step": 890
+    },
+    {
+      "epoch": 0.9544008483563097,
+      "grad_norm": 0.9112839698791504,
+      "learning_rate": 3.409331919406151e-05,
+      "loss": 0.3855,
+      "step": 900
+    },
+    {
+      "epoch": 0.9544008483563097,
+      "eval_loss": 0.5862192511558533,
+      "eval_runtime": 11.7865,
+      "eval_samples_per_second": 40.725,
+      "eval_steps_per_second": 2.545,
+      "step": 900
+    },
+    {
+      "epoch": 0.9650053022269353,
+      "grad_norm": 1.0250121355056763,
+      "learning_rate": 3.391657829621775e-05,
+      "loss": 0.4219,
+      "step": 910
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 1.045753836631775,
+      "learning_rate": 3.373983739837399e-05,
+      "loss": 0.3936,
+      "step": 920
+    },
+    {
+      "epoch": 0.9862142099681867,
+      "grad_norm": 1.0251036882400513,
+      "learning_rate": 3.356309650053022e-05,
+      "loss": 0.3798,
+      "step": 930
+    },
+    {
+      "epoch": 0.9968186638388123,
+      "grad_norm": 1.0625455379486084,
+      "learning_rate": 3.3386355602686466e-05,
+      "loss": 0.3779,
+      "step": 940
+    },
+    {
+      "epoch": 1.007423117709438,
+      "grad_norm": 1.050057291984558,
+      "learning_rate": 3.32096147048427e-05,
+      "loss": 0.3676,
+      "step": 950
+    },
+    {
+      "epoch": 1.007423117709438,
+      "eval_loss": 0.5891817212104797,
+      "eval_runtime": 11.7414,
+      "eval_samples_per_second": 40.881,
+      "eval_steps_per_second": 2.555,
+      "step": 950
+    },
+    {
+      "epoch": 1.0180275715800637,
+      "grad_norm": 1.109527826309204,
+      "learning_rate": 3.3032873806998944e-05,
+      "loss": 0.3532,
+      "step": 960
+    },
+    {
+      "epoch": 1.0286320254506893,
+      "grad_norm": 1.2735576629638672,
+      "learning_rate": 3.285613290915518e-05,
+      "loss": 0.3804,
+      "step": 970
+    },
+    {
+      "epoch": 1.039236479321315,
+      "grad_norm": 1.079765796661377,
+      "learning_rate": 3.267939201131142e-05,
+      "loss": 0.352,
+      "step": 980
+    },
+    {
+      "epoch": 1.0498409331919407,
+      "grad_norm": 1.069228172302246,
+      "learning_rate": 3.2502651113467655e-05,
+      "loss": 0.3402,
+      "step": 990
+    },
+    {
+      "epoch": 1.0604453870625663,
+      "grad_norm": 1.2578569650650024,
+      "learning_rate": 3.2325910215623894e-05,
+      "loss": 0.3541,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0604453870625663,
+      "eval_loss": 0.5981893539428711,
+      "eval_runtime": 11.7382,
+      "eval_samples_per_second": 40.892,
+      "eval_steps_per_second": 2.556,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2829,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.03073903853269e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872835407be2a0a95214d9cc3b7966660b3e25cbfda85f13ed9adad96c071793
+size 5880