Training in progress, epoch 4, 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": 0.075,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "o_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 sha256:638dbd1b9ade7a06d19b6821c034f1b84d60a69e296bb2462ec7d681f5c76657
+size 159967880

checkpoint-126/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5818f4a82d7604d4196255b19db7a54dc95af619c316d44a6a0b1e53409f171
+size 320084037

checkpoint-126/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e8e9e36db676d91f5c1ce82ca49114179b36fa25b6d04c0cd7f3513bcadc21
+size 14575

checkpoint-126/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e503cefd6ea7143c23d8d201e45f44441854804ed67615151f1c698523fb23c
+size 627

checkpoint-126/trainer_state.json

@@ -0,0 +1,823 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.006048387096774,
+  "eval_steps": 25,
+  "global_step": 126,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-05,
+      "loss": 4.2505,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 4.052073955535889,
+      "eval_runtime": 60.4806,
+      "eval_samples_per_second": 4.134,
+      "eval_steps_per_second": 4.134,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001,
+      "loss": 4.2141,
+      "step": 2
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00015,
+      "loss": 4.0033,
+      "step": 3
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0002,
+      "loss": 3.9023,
+      "step": 4
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00025,
+      "loss": 4.0955,
+      "step": 5
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 3.8902,
+      "step": 6
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00035,
+      "loss": 3.9076,
+      "step": 7
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0004,
+      "loss": 3.7008,
+      "step": 8
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00045000000000000004,
+      "loss": 3.7071,
+      "step": 9
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0005,
+      "loss": 3.6304,
+      "step": 10
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0004999782204181027,
+      "loss": 3.6851,
+      "step": 11
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0004999128854672123,
+      "loss": 3.4864,
+      "step": 12
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.000499804006531072,
+      "loss": 3.3743,
+      "step": 13
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0004996516025803834,
+      "loss": 3.2944,
+      "step": 14
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0004994557001695014,
+      "loss": 3.1978,
+      "step": 15
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0004992163334318065,
+      "loss": 3.0865,
+      "step": 16
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0004989335440737586,
+      "loss": 3.0893,
+      "step": 17
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0004986073813676296,
+      "loss": 2.9218,
+      "step": 18
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0004982379021429183,
+      "loss": 2.8753,
+      "step": 19
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0004978251707764492,
+      "loss": 2.7118,
+      "step": 20
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0004973692591811548,
+      "loss": 2.6693,
+      "step": 21
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0004968702467935468,
+      "loss": 2.474,
+      "step": 22
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0004963282205598744,
+      "loss": 2.3912,
+      "step": 23
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0004957432749209755,
+      "loss": 2.2401,
+      "step": 24
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0004951155117958217,
+      "loss": 2.1461,
+      "step": 25
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 2.080416202545166,
+      "eval_runtime": 61.4527,
+      "eval_samples_per_second": 4.068,
+      "eval_steps_per_second": 4.068,
+      "step": 25
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0004944450405637602,
+      "loss": 2.1114,
+      "step": 26
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0004937319780454559,
+      "loss": 1.8994,
+      "step": 27
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0004929764484825369,
+      "loss": 2.0342,
+      "step": 28
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0004921785835159472,
+      "loss": 2.0333,
+      "step": 29
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0004913385221630097,
+      "loss": 1.8424,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0004904564107932048,
+      "loss": 1.7993,
+      "step": 31
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.000489532403102667,
+      "loss": 1.7643,
+      "step": 32
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0004885666600874058,
+      "loss": 1.8718,
+      "step": 33
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00048755935001525374,
+      "loss": 1.7178,
+      "step": 34
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0004865106483965487,
+      "loss": 1.7185,
+      "step": 35
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0004854207379535529,
+      "loss": 1.7702,
+      "step": 36
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00048428980858861636,
+      "loss": 1.7089,
+      "step": 37
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00048311805735108893,
+      "loss": 1.6515,
+      "step": 38
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.000481905688402987,
+      "loss": 1.7014,
+      "step": 39
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0004806529129834207,
+      "loss": 1.5697,
+      "step": 40
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0004793599493717891,
+      "loss": 1.6295,
+      "step": 41
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00047802702284974695,
+      "loss": 1.4599,
+      "step": 42
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0004766543656619532,
+      "loss": 1.5082,
+      "step": 43
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00047524221697560476,
+      "loss": 1.4499,
+      "step": 44
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00047379082283876563,
+      "loss": 1.432,
+      "step": 45
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0004723004361374953,
+      "loss": 1.4362,
+      "step": 46
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0004707713165517877,
+      "loss": 1.4588,
+      "step": 47
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.0004692037305103247,
+      "loss": 1.4489,
+      "step": 48
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0004675979511440549,
+      "loss": 1.3382,
+      "step": 49
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00046595425823860404,
+      "loss": 1.3896,
+      "step": 50
+    },
+    {
+      "epoch": 1.59,
+      "eval_loss": 1.4752908945083618,
+      "eval_runtime": 61.5879,
+      "eval_samples_per_second": 4.059,
+      "eval_steps_per_second": 4.059,
+      "step": 50
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0004642729381855262,
+      "loss": 1.3671,
+      "step": 51
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0004625542839324036,
+      "loss": 1.3629,
+      "step": 52
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00046079859493180467,
+      "loss": 1.3171,
+      "step": 53
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00045900617708910854,
+      "loss": 1.4639,
+      "step": 54
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0004571773427092047,
+      "loss": 1.3031,
+      "step": 55
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00045531241044207836,
+      "loss": 1.3329,
+      "step": 56
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00045341170522729,
+      "loss": 1.3298,
+      "step": 57
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00045147555823735875,
+      "loss": 1.3794,
+      "step": 58
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00044950430682005996,
+      "loss": 1.3068,
+      "step": 59
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.00044749829443964704,
+      "loss": 1.3701,
+      "step": 60
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0004454578706170075,
+      "loss": 1.2326,
+      "step": 61
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.0004433833908687633,
+      "loss": 1.1632,
+      "step": 62
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.00044127521664532704,
+      "loss": 1.3177,
+      "step": 63
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.000439133715267924,
+      "loss": 1.2388,
+      "step": 64
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.0004369592598645911,
+      "loss": 1.162,
+      "step": 65
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00043475222930516476,
+      "loss": 1.2373,
+      "step": 66
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.0004325130081352675,
+      "loss": 1.2125,
+      "step": 67
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.00043024198650930625,
+      "loss": 1.2374,
+      "step": 68
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.0004279395601224928,
+      "loss": 1.2134,
+      "step": 69
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.0004256061301418996,
+      "loss": 1.2564,
+      "step": 70
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00042324210313656173,
+      "loss": 1.1408,
+      "step": 71
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00042084789100663714,
+      "loss": 1.1333,
+      "step": 72
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.0004184239109116393,
+      "loss": 1.1668,
+      "step": 73
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 0.0004159705851977521,
+      "loss": 1.1727,
+      "step": 74
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.0004159705851977521,
+      "loss": 1.2477,
+      "step": 75
+    },
+    {
+      "epoch": 2.38,
+      "eval_loss": 1.3385169506072998,
+      "eval_runtime": 61.3886,
+      "eval_samples_per_second": 4.072,
+      "eval_steps_per_second": 4.072,
+      "step": 75
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.0004134883413242421,
+      "loss": 1.149,
+      "step": 76
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 0.0004109776117889789,
+      "loss": 1.2062,
+      "step": 77
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.00040843883405307905,
+      "loss": 1.1129,
+      "step": 78
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 0.0004058724504646834,
+      "loss": 1.162,
+      "step": 79
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 0.00040327890818188427,
+      "loss": 1.0549,
+      "step": 80
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 0.00040327890818188427,
+      "loss": 2.1276,
+      "step": 81
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.00040327890818188427,
+      "loss": 1.173,
+      "step": 82
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 1.1439,
+      "step": 83
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 1.4863,
+      "step": 84
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 1.819,
+      "step": 85
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 1.5314,
+      "step": 86
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 1.2033,
+      "step": 87
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 1.9072,
+      "step": 88
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 2.0276,
+      "step": 89
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 1.5355,
+      "step": 90
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 1.1985,
+      "step": 91
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 2.2275,
+      "step": 92
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 2.7711,
+      "step": 93
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0004006586590948141,
+      "loss": 1.9637,
+      "step": 94
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0003980121597469096,
+      "loss": 1.175,
+      "step": 95
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 0.000395339871255365,
+      "loss": 1.093,
+      "step": 96
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 0.00039264225923078876,
+      "loss": 1.0794,
+      "step": 97
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 0.00038991979369607703,
+      "loss": 1.1933,
+      "step": 98
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 0.0003871729490045185,
+      "loss": 1.0789,
+      "step": 99
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 0.00038440220375714435,
+      "loss": 1.0748,
+      "step": 100
+    },
+    {
+      "epoch": 3.17,
+      "eval_loss": 1.3322774171829224,
+      "eval_runtime": 61.5642,
+      "eval_samples_per_second": 4.061,
+      "eval_steps_per_second": 4.061,
+      "step": 100
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 0.00038160804071933895,
+      "loss": 1.0428,
+      "step": 101
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 0.000378790946736724,
+      "loss": 0.9776,
+      "step": 102
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 0.0003759514126503324,
+      "loss": 1.0653,
+      "step": 103
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 0.0003730899332110855,
+      "loss": 1.0331,
+      "step": 104
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.00037020700699358984,
+      "loss": 1.0289,
+      "step": 105
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 0.0003673031363092666,
+      "loss": 1.0181,
+      "step": 106
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 0.0003643788271188308,
+      "loss": 1.0117,
+      "step": 107
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 0.0003614345889441346,
+      "loss": 1.0623,
+      "step": 108
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 0.00035847093477938953,
+      "loss": 0.9958,
+      "step": 109
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 0.0003554883810017844,
+      "loss": 1.0066,
+      "step": 110
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 0.00035248744728151344,
+      "loss": 1.0598,
+      "step": 111
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 0.0003494686564912302,
+      "loss": 1.0502,
+      "step": 112
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 0.0003464325346149449,
+      "loss": 1.0306,
+      "step": 113
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 0.0003433796106563779,
+      "loss": 0.9659,
+      "step": 114
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 0.0003403104165467883,
+      "loss": 1.1223,
+      "step": 115
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.0003372254870522917,
+      "loss": 1.097,
+      "step": 116
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 0.0003341253596806848,
+      "loss": 0.9847,
+      "step": 117
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 0.0003310105745877915,
+      "loss": 1.0495,
+      "step": 118
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 0.0003278816744833479,
+      "loss": 1.0697,
+      "step": 119
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.0003247392045364426,
+      "loss": 1.1284,
+      "step": 120
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 0.0003215837122805282,
+      "loss": 0.9914,
+      "step": 121
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 0.0003184157475180208,
+      "loss": 1.035,
+      "step": 122
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 0.00031523586222450417,
+      "loss": 1.0098,
+      "step": 123
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 0.000312044610452556,
+      "loss": 1.0373,
+      "step": 124
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 0.00030884254823521063,
+      "loss": 1.0539,
+      "step": 125
+    },
+    {
+      "epoch": 3.97,
+      "eval_loss": 1.29022216796875,
+      "eval_runtime": 61.524,
+      "eval_samples_per_second": 4.063,
+      "eval_steps_per_second": 4.063,
+      "step": 125
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 0.0003056302334890786,
+      "loss": 0.9474,
+      "step": 126
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 248,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 1.653249250814853e+17,
+  "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:ebc1ba8de529c7c32cc6ab052beaeb5c04d634fe0a2b1904e12ba3ec54228a80
+size 4603