Training in progress, epoch 1, checkpoint

checkpoint-126/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: yentinglin/Taiwan-LLM-7B-v2.0-chat
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.0

checkpoint-126/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "yentinglin/Taiwan-LLM-7B-v2.0-chat",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-126/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af22ad5df74625210713ef368d0b02c7f058adca19bded43a1f2e84795a71ec9
+size 40036040

checkpoint-126/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d39892cb0e6c164834644982c11eeeae410662780f6379a691fe1399c9880c
+size 80218053

checkpoint-126/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd71f7eb73f30bec98c585c9720ca9b3062fbbfa7f2d0655d840524ceb405b6
+size 14575

checkpoint-126/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc28c2798df4d985bf5e974db0962dc19ccd75c172c3e2c7b01514ef56d473c3
+size 627

checkpoint-126/trainer_state.json

@@ -0,0 +1,823 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0161290322580645,
+  "eval_steps": 25,
+  "global_step": 126,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0,
+      "loss": 4.0553,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 4.052073955535889,
+      "eval_runtime": 57.3905,
+      "eval_samples_per_second": 4.356,
+      "eval_steps_per_second": 4.356,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2e-05,
+      "loss": 4.3696,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 4.2401,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-05,
+      "loss": 4.3077,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 4.0741,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001,
+      "loss": 4.1673,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00012,
+      "loss": 3.9378,
+      "step": 7
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00014,
+      "loss": 4.0167,
+      "step": 8
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00016,
+      "loss": 3.5818,
+      "step": 9
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00018,
+      "loss": 3.9022,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0002,
+      "loss": 3.7906,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0001999979107245606,
+      "loss": 3.6776,
+      "step": 12
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019999164298554375,
+      "loss": 3.4291,
+      "step": 13
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019998119704485014,
+      "loss": 3.6101,
+      "step": 14
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019996657333896877,
+      "loss": 3.5537,
+      "step": 15
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019994777247895855,
+      "loss": 3.386,
+      "step": 16
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019992479525042303,
+      "loss": 3.6359,
+      "step": 17
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019989764261347736,
+      "loss": 3.6132,
+      "step": 18
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019986631570270832,
+      "loss": 3.4794,
+      "step": 19
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019983081582712685,
+      "loss": 3.2395,
+      "step": 20
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019979114447011323,
+      "loss": 3.2974,
+      "step": 21
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019974730328935534,
+      "loss": 3.2698,
+      "step": 22
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0001996992941167792,
+      "loss": 3.3091,
+      "step": 23
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019964711895847258,
+      "loss": 3.2017,
+      "step": 24
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019959077999460095,
+      "loss": 3.2469,
+      "step": 25
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 3.0720062255859375,
+      "eval_runtime": 61.8274,
+      "eval_samples_per_second": 4.044,
+      "eval_steps_per_second": 4.044,
+      "step": 25
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019953027957931658,
+      "loss": 3.1102,
+      "step": 26
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019946562024066014,
+      "loss": 3.1641,
+      "step": 27
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019939680468045499,
+      "loss": 2.9779,
+      "step": 28
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019932383577419432,
+      "loss": 3.104,
+      "step": 29
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019924671657092096,
+      "loss": 2.7981,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019916545029310012,
+      "loss": 2.7673,
+      "step": 31
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019908004033648453,
+      "loss": 2.8478,
+      "step": 32
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019899049026997272,
+      "loss": 2.7539,
+      "step": 33
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019889680383545973,
+      "loss": 2.726,
+      "step": 34
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019879898494768093,
+      "loss": 2.81,
+      "step": 35
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019869703769404828,
+      "loss": 2.6177,
+      "step": 36
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019859096633447965,
+      "loss": 2.6046,
+      "step": 37
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 2.5004,
+      "step": 38
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001983664691986601,
+      "loss": 2.4993,
+      "step": 39
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019824805280313623,
+      "loss": 2.2775,
+      "step": 40
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019812553106273847,
+      "loss": 2.3306,
+      "step": 41
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019799890909710013,
+      "loss": 2.236,
+      "step": 42
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019786819219718443,
+      "loss": 2.2798,
+      "step": 43
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001977333858250636,
+      "loss": 2.2178,
+      "step": 44
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019759449561369038,
+      "loss": 1.9915,
+      "step": 45
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019745152736666302,
+      "loss": 2.3066,
+      "step": 46
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019730448705798239,
+      "loss": 2.1409,
+      "step": 47
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019715338083180269,
+      "loss": 1.9976,
+      "step": 48
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019699821500217434,
+      "loss": 2.1843,
+      "step": 49
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0001968389960527806,
+      "loss": 2.1539,
+      "step": 50
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.9486372470855713,
+      "eval_runtime": 61.7944,
+      "eval_samples_per_second": 4.046,
+      "eval_steps_per_second": 4.046,
+      "step": 50
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001966757306366662,
+      "loss": 2.2096,
+      "step": 51
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019650842557595967,
+      "loss": 2.0241,
+      "step": 52
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019633708786158806,
+      "loss": 1.8814,
+      "step": 53
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019616172465298492,
+      "loss": 1.9953,
+      "step": 54
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019598234327779118,
+      "loss": 1.9807,
+      "step": 55
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0001957989512315489,
+      "loss": 1.9743,
+      "step": 56
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00019561155617738797,
+      "loss": 1.867,
+      "step": 57
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00019542016594570615,
+      "loss": 1.8289,
+      "step": 58
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00019522478853384155,
+      "loss": 1.9712,
+      "step": 59
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00019502543210573881,
+      "loss": 1.6946,
+      "step": 60
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00019482210499160765,
+      "loss": 1.8674,
+      "step": 61
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00019461481568757506,
+      "loss": 1.6849,
+      "step": 62
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00019440357285533,
+      "loss": 1.7003,
+      "step": 63
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00019418838532176173,
+      "loss": 1.7021,
+      "step": 64
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 1.8302,
+      "step": 65
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0001937462122819935,
+      "loss": 1.8549,
+      "step": 66
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.000193519245252219,
+      "loss": 1.8946,
+      "step": 67
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0001932883704732001,
+      "loss": 1.799,
+      "step": 68
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00019305359759215685,
+      "loss": 1.7541,
+      "step": 69
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00019281493641919368,
+      "loss": 1.7145,
+      "step": 70
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00019257239692688907,
+      "loss": 1.8254,
+      "step": 71
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00019232598924987903,
+      "loss": 1.6161,
+      "step": 72
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00019207572368443385,
+      "loss": 1.5698,
+      "step": 73
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00019182161068802741,
+      "loss": 1.8155,
+      "step": 74
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0001915636608789006,
+      "loss": 1.6997,
+      "step": 75
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 1.6153544187545776,
+      "eval_runtime": 61.8069,
+      "eval_samples_per_second": 4.045,
+      "eval_steps_per_second": 4.045,
+      "step": 75
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00019130188503561741,
+      "loss": 1.6507,
+      "step": 76
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001910362940966147,
+      "loss": 1.6035,
+      "step": 77
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00019076689915974488,
+      "loss": 1.4493,
+      "step": 78
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00019049371148181253,
+      "loss": 1.5494,
+      "step": 79
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0001902167424781038,
+      "loss": 1.5386,
+      "step": 80
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00018993600372190932,
+      "loss": 1.467,
+      "step": 81
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00018965150694404094,
+      "loss": 1.6658,
+      "step": 82
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00018936326403234125,
+      "loss": 1.6175,
+      "step": 83
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00018907128703118695,
+      "loss": 1.6551,
+      "step": 84
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00018877558814098561,
+      "loss": 1.409,
+      "step": 85
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00018847617971766577,
+      "loss": 1.4879,
+      "step": 86
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0001881730742721608,
+      "loss": 1.3067,
+      "step": 87
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00018786628446988593,
+      "loss": 1.6869,
+      "step": 88
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001875558231302091,
+      "loss": 1.5962,
+      "step": 89
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00018724170322591537,
+      "loss": 1.3352,
+      "step": 90
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00018692393788266479,
+      "loss": 1.5016,
+      "step": 91
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 1.6951,
+      "step": 92
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00018627752414301086,
+      "loss": 1.5388,
+      "step": 93
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00018594890275733453,
+      "loss": 1.3656,
+      "step": 94
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00018561668995302667,
+      "loss": 1.4599,
+      "step": 95
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0001852808996117683,
+      "loss": 1.3428,
+      "step": 96
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00018494154576472976,
+      "loss": 1.2147,
+      "step": 97
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0001845986425919841,
+      "loss": 1.4761,
+      "step": 98
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00018425220442191495,
+      "loss": 1.4571,
+      "step": 99
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00018390224573061747,
+      "loss": 1.5076,
+      "step": 100
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 1.49380362033844,
+      "eval_runtime": 61.7975,
+      "eval_samples_per_second": 4.045,
+      "eval_steps_per_second": 4.045,
+      "step": 100
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00018354878114129367,
+      "loss": 1.3776,
+      "step": 101
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00018319182542364117,
+      "loss": 1.437,
+      "step": 102
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00018283139349323634,
+      "loss": 1.3558,
+      "step": 103
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0001824675004109107,
+      "loss": 1.4502,
+      "step": 104
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00018210016138212187,
+      "loss": 1.3451,
+      "step": 105
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00018172939175631808,
+      "loss": 1.403,
+      "step": 106
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00018135520702629675,
+      "loss": 1.1523,
+      "step": 107
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00018097762282755727,
+      "loss": 1.2302,
+      "step": 108
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00018059665493764743,
+      "loss": 1.4151,
+      "step": 109
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0001802123192755044,
+      "loss": 1.4853,
+      "step": 110
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0001798246319007893,
+      "loss": 1.2571,
+      "step": 111
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0001794336090132164,
+      "loss": 1.3594,
+      "step": 112
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00017903926695187595,
+      "loss": 1.3997,
+      "step": 113
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00017864162219455163,
+      "loss": 1.5718,
+      "step": 114
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00017824069135703198,
+      "loss": 1.314,
+      "step": 115
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00017783649119241602,
+      "loss": 1.3595,
+      "step": 116
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00017742903859041325,
+      "loss": 1.4467,
+      "step": 117
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00017701835057663798,
+      "loss": 1.2837,
+      "step": 118
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 1.2669,
+      "step": 119
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00017618733709147662,
+      "loss": 1.3115,
+      "step": 120
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0001757670463444118,
+      "loss": 1.1836,
+      "step": 121
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00017534358963276607,
+      "loss": 1.6092,
+      "step": 122
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00017491698465089362,
+      "loss": 1.2288,
+      "step": 123
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00017448724922470058,
+      "loss": 1.2305,
+      "step": 124
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00017405440131090048,
+      "loss": 1.3794,
+      "step": 125
+    },
+    {
+      "epoch": 1.01,
+      "eval_loss": 1.4039632081985474,
+      "eval_runtime": 61.7879,
+      "eval_samples_per_second": 4.046,
+      "eval_steps_per_second": 4.046,
+      "step": 125
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00017361845899626355,
+      "loss": 1.2283,
+      "step": 126
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 496,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 4.12261207202857e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-126/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29182789cc886c4cb1e203599999900c580a72f92286132414128006e2d749f4
+size 4603