Training in progress, step 2200, checkpoint

checkpoint-2200/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: unsloth/gemma-7b-bnb-4bit
+---
+
+# 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 0.10.0

checkpoint-2200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-7b-bnb-4bit",
+  "bias": "none",
+  "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": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bbf856104181f9725143aa31a49a533a4f4cf5ed538da0e4cdb0ccf62aea6d8
+size 100059752

checkpoint-2200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838bea0bbb4d23246a7f5eb1ef6ad8b8bcc9b50d7416308f2e7d63e195518481
+size 50541492

checkpoint-2200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:686877537a25809890c7dcabc7ee919c6e46d71e43342a4d8f0aeedcdc7a7982
+size 14512

checkpoint-2200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8296edcb09362e52fc93c3ba63ecb045aefefcf7f60951f3e5deb9999cb7145f
+size 14512

checkpoint-2200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:894b8cf6a0fd576c09ccc807f35583b9415c18ecf988cebabe9fbf57209b527d
+size 1192

checkpoint-2200/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2200/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

checkpoint-2200/tokenizer_config.json

@@ -0,0 +1,72 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\\n' + content + '\\n\\n### Response:\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<eos>' + '\\n\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-2200/trainer_state.json

@@ -0,0 +1,505 @@
+{
+  "best_metric": 1.8768367767333984,
+  "best_model_checkpoint": "/kaggle/working/gemma/checkpoint-1600",
+  "epoch": 0.8654602675059009,
+  "eval_steps": 100,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.6322383880615234,
+      "learning_rate": 0.0003,
+      "loss": 4.1999,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.3033926486968994,
+      "learning_rate": 0.0003,
+      "loss": 2.1859,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 2.0820870399475098,
+      "eval_runtime": 110.3393,
+      "eval_samples_per_second": 0.933,
+      "eval_steps_per_second": 0.236,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.6072160005569458,
+      "learning_rate": 0.0003,
+      "loss": 2.1419,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.4586890935897827,
+      "learning_rate": 0.0003,
+      "loss": 2.1001,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 1.99821937084198,
+      "eval_runtime": 110.16,
+      "eval_samples_per_second": 0.935,
+      "eval_steps_per_second": 0.236,
+      "step": 200
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.309139370918274,
+      "learning_rate": 0.0003,
+      "loss": 2.0746,
+      "step": 250
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.487611174583435,
+      "learning_rate": 0.0003,
+      "loss": 2.0647,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.9572771787643433,
+      "eval_runtime": 109.5937,
+      "eval_samples_per_second": 0.94,
+      "eval_steps_per_second": 0.237,
+      "step": 300
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.494892954826355,
+      "learning_rate": 0.0003,
+      "loss": 2.0195,
+      "step": 350
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.4196828603744507,
+      "learning_rate": 0.0003,
+      "loss": 2.0195,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 1.9236102104187012,
+      "eval_runtime": 109.859,
+      "eval_samples_per_second": 0.938,
+      "eval_steps_per_second": 0.237,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.7659281492233276,
+      "learning_rate": 0.0003,
+      "loss": 1.9753,
+      "step": 450
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.059668779373169,
+      "learning_rate": 0.0003,
+      "loss": 1.9975,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.9109984636306763,
+      "eval_runtime": 109.5777,
+      "eval_samples_per_second": 0.94,
+      "eval_steps_per_second": 0.237,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.3529094457626343,
+      "learning_rate": 0.0003,
+      "loss": 1.9846,
+      "step": 550
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.4471253156661987,
+      "learning_rate": 0.0003,
+      "loss": 1.9809,
+      "step": 600
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 1.9085875749588013,
+      "eval_runtime": 109.6643,
+      "eval_samples_per_second": 0.939,
+      "eval_steps_per_second": 0.237,
+      "step": 600
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.965285301208496,
+      "learning_rate": 0.0003,
+      "loss": 2.0156,
+      "step": 650
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.1004948616027832,
+      "learning_rate": 0.0003,
+      "loss": 2.0118,
+      "step": 700
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.9014776945114136,
+      "eval_runtime": 109.9343,
+      "eval_samples_per_second": 0.937,
+      "eval_steps_per_second": 0.237,
+      "step": 700
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.5002790689468384,
+      "learning_rate": 0.0003,
+      "loss": 1.9538,
+      "step": 750
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.2678498029708862,
+      "learning_rate": 0.0003,
+      "loss": 1.9402,
+      "step": 800
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 1.8954542875289917,
+      "eval_runtime": 110.006,
+      "eval_samples_per_second": 0.936,
+      "eval_steps_per_second": 0.236,
+      "step": 800
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.2786470651626587,
+      "learning_rate": 0.0003,
+      "loss": 1.9687,
+      "step": 850
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.6264179944992065,
+      "learning_rate": 0.0003,
+      "loss": 1.9531,
+      "step": 900
+    },
+    {
+      "epoch": 0.35,
+      "eval_loss": 1.8900243043899536,
+      "eval_runtime": 110.1408,
+      "eval_samples_per_second": 0.935,
+      "eval_steps_per_second": 0.236,
+      "step": 900
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.2318661212921143,
+      "learning_rate": 0.0003,
+      "loss": 1.9663,
+      "step": 950
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.4853723049163818,
+      "learning_rate": 0.0003,
+      "loss": 1.9804,
+      "step": 1000
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 1.896203875541687,
+      "eval_runtime": 109.686,
+      "eval_samples_per_second": 0.939,
+      "eval_steps_per_second": 0.237,
+      "step": 1000
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.1880249977111816,
+      "learning_rate": 0.0003,
+      "loss": 1.9693,
+      "step": 1050
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 2.1265156269073486,
+      "learning_rate": 0.0003,
+      "loss": 1.9953,
+      "step": 1100
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 1.8932738304138184,
+      "eval_runtime": 109.7941,
+      "eval_samples_per_second": 0.938,
+      "eval_steps_per_second": 0.237,
+      "step": 1100
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.2788913249969482,
+      "learning_rate": 0.0003,
+      "loss": 1.9427,
+      "step": 1150
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.2446949481964111,
+      "learning_rate": 0.0003,
+      "loss": 1.9435,
+      "step": 1200
+    },
+    {
+      "epoch": 0.47,
+      "eval_loss": 1.891483187675476,
+      "eval_runtime": 109.743,
+      "eval_samples_per_second": 0.939,
+      "eval_steps_per_second": 0.237,
+      "step": 1200
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.5069431066513062,
+      "learning_rate": 0.0003,
+      "loss": 1.9891,
+      "step": 1250
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.3292410373687744,
+      "learning_rate": 0.0003,
+      "loss": 1.9804,
+      "step": 1300
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 1.8822150230407715,
+      "eval_runtime": 109.7975,
+      "eval_samples_per_second": 0.938,
+      "eval_steps_per_second": 0.237,
+      "step": 1300
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.274938941001892,
+      "learning_rate": 0.0003,
+      "loss": 1.9754,
+      "step": 1350
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.5717120170593262,
+      "learning_rate": 0.0003,
+      "loss": 1.9758,
+      "step": 1400
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 1.8797138929367065,
+      "eval_runtime": 109.9298,
+      "eval_samples_per_second": 0.937,
+      "eval_steps_per_second": 0.237,
+      "step": 1400
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.445812463760376,
+      "learning_rate": 0.0003,
+      "loss": 1.9378,
+      "step": 1450
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.3848668336868286,
+      "learning_rate": 0.0003,
+      "loss": 1.9472,
+      "step": 1500
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 1.8788877725601196,
+      "eval_runtime": 109.275,
+      "eval_samples_per_second": 0.943,
+      "eval_steps_per_second": 0.238,
+      "step": 1500
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.536832332611084,
+      "learning_rate": 0.0003,
+      "loss": 1.9483,
+      "step": 1550
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.37943696975708,
+      "learning_rate": 0.0003,
+      "loss": 1.9507,
+      "step": 1600
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 1.8768367767333984,
+      "eval_runtime": 109.2487,
+      "eval_samples_per_second": 0.943,
+      "eval_steps_per_second": 0.238,
+      "step": 1600
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.1901755332946777,
+      "learning_rate": 0.0003,
+      "loss": 1.9402,
+      "step": 1650
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0710890293121338,
+      "learning_rate": 0.0003,
+      "loss": 1.9488,
+      "step": 1700
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.884979009628296,
+      "eval_runtime": 109.08,
+      "eval_samples_per_second": 0.944,
+      "eval_steps_per_second": 0.238,
+      "step": 1700
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.2577444314956665,
+      "learning_rate": 0.0003,
+      "loss": 1.9571,
+      "step": 1750
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 2.273926258087158,
+      "learning_rate": 0.0003,
+      "loss": 1.9708,
+      "step": 1800
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 1.8852429389953613,
+      "eval_runtime": 109.1066,
+      "eval_samples_per_second": 0.944,
+      "eval_steps_per_second": 0.238,
+      "step": 1800
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.308111548423767,
+      "learning_rate": 0.0003,
+      "loss": 1.989,
+      "step": 1850
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.5021519660949707,
+      "learning_rate": 0.0003,
+      "loss": 1.9692,
+      "step": 1900
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.8924355506896973,
+      "eval_runtime": 108.9102,
+      "eval_samples_per_second": 0.946,
+      "eval_steps_per_second": 0.239,
+      "step": 1900
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.4355289936065674,
+      "learning_rate": 0.0003,
+      "loss": 1.948,
+      "step": 1950
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.268176794052124,
+      "learning_rate": 0.0003,
+      "loss": 1.9708,
+      "step": 2000
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 1.8840947151184082,
+      "eval_runtime": 109.0758,
+      "eval_samples_per_second": 0.944,
+      "eval_steps_per_second": 0.238,
+      "step": 2000
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.141319990158081,
+      "learning_rate": 0.0003,
+      "loss": 1.9651,
+      "step": 2050
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.4737452268600464,
+      "learning_rate": 0.0003,
+      "loss": 1.976,
+      "step": 2100
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 1.8879451751708984,
+      "eval_runtime": 109.5286,
+      "eval_samples_per_second": 0.94,
+      "eval_steps_per_second": 0.237,
+      "step": 2100
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.5503915548324585,
+      "learning_rate": 0.0003,
+      "loss": 1.9487,
+      "step": 2150
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.513409972190857,
+      "learning_rate": 0.0003,
+      "loss": 1.9337,
+      "step": 2200
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 1.8889082670211792,
+      "eval_runtime": 109.4713,
+      "eval_samples_per_second": 0.941,
+      "eval_steps_per_second": 0.238,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 12710,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "total_flos": 1.851841171907674e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa6a145827ab3567f8d35dec10f844e10312812d3470e09d369a923854ee9fe
+size 5112