Upload folder using huggingface_hub

102_128_e3_3e-5/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

102_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1acce531d47ad5b6f876087273bb3f2b4bae3d7b54ab0ef3dc12ddf405cd144c
+size 791751704

102_128_e3_3e-5/added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "<|end_of_cite|>": 49156,
+  "<|end_of_plugin|>": 49158,
+  "<|end_of_role|>": 49153,
+  "<|start_of_cite|>": 49155,
+  "<|start_of_plugin|>": 49157,
+  "<|start_of_role|>": 49152,
+  "<|tool_call|>": 49154
+}

102_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 8.274115317328773e+17,
+    "train_loss": 0.37865535192417377,
+    "train_runtime": 384.2891,
+    "train_samples": 6334,
+    "train_samples_per_second": 49.447,
+    "train_steps_per_second": 1.546
+}

102_128_e3_3e-5/chat_template.jinja

@@ -0,0 +1,62 @@
+{# Alias tools -> available_tools #}
+{%- if tools and not available_tools -%}
+    {%- set available_tools = tools -%}
+{%- endif -%}
+{%- if messages[0]['role'] == 'system' %}
+     {%- set system_message = messages[0]['content'] %}
+     {%- set loop_messages = messages[1:] %}
+ {%- else %}
+     {%- set system_message = "Knowledge Cutoff Date: April 2024.
+Today's Date: " + strftime_now('%B %d, %Y') + ".
+You are Granite, developed by IBM." %}
+     {%- if available_tools and documents %}
+         {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.
+Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+     {%- elif available_tools %}
+         {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request." %}
+     {%- elif documents %}
+         {%- set system_message = system_message + " Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+    {%- elif thinking %}
+    {%- set system_message = system_message + " You are a helpful AI assistant.
+Respond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query." %}
+     {%- else %}
+         {%- set system_message = system_message + " You are a helpful AI assistant." %}
+     {%- endif %}
+     {%- if 'citations' in controls and documents %}
+         {%- set system_message = system_message + '
+Use the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}
+     {%- endif %}
+     {%- if 'hallucinations' in controls and documents %}
+         {%- set system_message = system_message + '
+Finally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}
+     {%- endif %}
+     {%- set loop_messages = messages %}
+ {%- endif %}
+ {{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>
+' }}
+ {%- if available_tools %}
+     {{- '<|start_of_role|>available_tools<|end_of_role|>' }}
+     {{- available_tools | tojson(indent=4) }}
+     {{- '<|end_of_text|>
+' }}
+ {%- endif %}
+ {%- if documents %}
+     {%- for document in documents %}
+         {{- '<|start_of_role|>document {"document_id": "' + document['doc_id'] | string + '"}<|end_of_role|>
+' }}
+         {{- document['text'] }}
+         {{- '<|end_of_text|>
+' }}
+              {%- endfor %}
+ {%- endif %}
+ {%- for message in loop_messages %}
+     {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
+' }}
+     {%- if loop.last and add_generation_prompt %}
+         {{- '<|start_of_role|>assistant' }}
+             {%- if controls %}
+                 {{- ' ' + controls | tojson()}}
+             {%- endif %}
+         {{- '<|end_of_role|>' }}
+     {%- endif %}
+ {%- endfor %}

102_128_e3_3e-5/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12800,
+  "logits_scaling": 16.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 49159
+}

102_128_e3_3e-5/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>",
+    "<|start_of_cite|>",
+    "<|end_of_cite|>",
+    "<|start_of_plugin|>",
+    "<|end_of_plugin|>"
+  ],
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_plugin|>",
+  "unk_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

102_128_e3_3e-5/tokenizer_config.json

@@ -0,0 +1,234 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49154": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49155": {
+      "content": "<|start_of_cite|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49156": {
+      "content": "<|end_of_cite|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49157": {
+      "content": "<|start_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49158": {
+      "content": "<|end_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>",
+    "<|start_of_cite|>",
+    "<|end_of_cite|>",
+    "<|start_of_plugin|>",
+    "<|end_of_plugin|>"
+  ],
+  "bos_token": "<|end_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|end_of_plugin|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|end_of_text|>",
+  "vocab_size": 49152
+}

102_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 8.274115317328773e+17,
+    "train_loss": 0.37865535192417377,
+    "train_runtime": 384.2891,
+    "train_samples": 6334,
+    "train_samples_per_second": 49.447,
+    "train_steps_per_second": 1.546
+}

102_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,869 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 594,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.025252525252525252,
+      "grad_norm": 2.2151217460632324,
+      "learning_rate": 4e-06,
+      "loss": 1.5477,
+      "step": 5
+    },
+    {
+      "epoch": 0.050505050505050504,
+      "grad_norm": 1.1283358335494995,
+      "learning_rate": 9e-06,
+      "loss": 1.4754,
+      "step": 10
+    },
+    {
+      "epoch": 0.07575757575757576,
+      "grad_norm": 0.5498894453048706,
+      "learning_rate": 1.4e-05,
+      "loss": 1.4267,
+      "step": 15
+    },
+    {
+      "epoch": 0.10101010101010101,
+      "grad_norm": 0.9591898918151855,
+      "learning_rate": 1.9e-05,
+      "loss": 1.4045,
+      "step": 20
+    },
+    {
+      "epoch": 0.12626262626262627,
+      "grad_norm": 0.4227151870727539,
+      "learning_rate": 2.4e-05,
+      "loss": 1.3284,
+      "step": 25
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 0.4570218622684479,
+      "learning_rate": 2.9e-05,
+      "loss": 1.2953,
+      "step": 30
+    },
+    {
+      "epoch": 0.17676767676767677,
+      "grad_norm": 0.3928327262401581,
+      "learning_rate": 2.9996276899008885e-05,
+      "loss": 1.303,
+      "step": 35
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 0.4276125729084015,
+      "learning_rate": 2.9981154968741788e-05,
+      "loss": 1.2947,
+      "step": 40
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 0.40105757117271423,
+      "learning_rate": 2.9954413235354147e-05,
+      "loss": 1.1973,
+      "step": 45
+    },
+    {
+      "epoch": 0.25252525252525254,
+      "grad_norm": 0.4401269853115082,
+      "learning_rate": 2.9916072440482896e-05,
+      "loss": 1.1959,
+      "step": 50
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.4584244191646576,
+      "learning_rate": 2.9866162322321703e-05,
+      "loss": 1.0593,
+      "step": 55
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 0.5520833730697632,
+      "learning_rate": 2.980472159255521e-05,
+      "loss": 1.0806,
+      "step": 60
+    },
+    {
+      "epoch": 0.3282828282828283,
+      "grad_norm": 0.489409476518631,
+      "learning_rate": 2.973179790633317e-05,
+      "loss": 1.0332,
+      "step": 65
+    },
+    {
+      "epoch": 0.35353535353535354,
+      "grad_norm": 0.5482374429702759,
+      "learning_rate": 2.964744782530777e-05,
+      "loss": 1.0705,
+      "step": 70
+    },
+    {
+      "epoch": 0.3787878787878788,
+      "grad_norm": 0.5979885458946228,
+      "learning_rate": 2.955173677376284e-05,
+      "loss": 1.0012,
+      "step": 75
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.6455130577087402,
+      "learning_rate": 2.9444738987868933e-05,
+      "loss": 0.9652,
+      "step": 80
+    },
+    {
+      "epoch": 0.4292929292929293,
+      "grad_norm": 0.6027261018753052,
+      "learning_rate": 2.9326537458103687e-05,
+      "loss": 0.9276,
+      "step": 85
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.6261054277420044,
+      "learning_rate": 2.9197223864882085e-05,
+      "loss": 0.8405,
+      "step": 90
+    },
+    {
+      "epoch": 0.4797979797979798,
+      "grad_norm": 0.6539518237113953,
+      "learning_rate": 2.9056898507446553e-05,
+      "loss": 0.8656,
+      "step": 95
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "grad_norm": 0.7583935260772705,
+      "learning_rate": 2.890567022607206e-05,
+      "loss": 0.8476,
+      "step": 100
+    },
+    {
+      "epoch": 0.5303030303030303,
+      "grad_norm": 0.7800160050392151,
+      "learning_rate": 2.8743656317646575e-05,
+      "loss": 0.7966,
+      "step": 105
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.8062440156936646,
+      "learning_rate": 2.8570982444692272e-05,
+      "loss": 0.7614,
+      "step": 110
+    },
+    {
+      "epoch": 0.5808080808080808,
+      "grad_norm": 0.7557229399681091,
+      "learning_rate": 2.838778253789822e-05,
+      "loss": 0.7803,
+      "step": 115
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.7781174182891846,
+      "learning_rate": 2.8194198692239936e-05,
+      "loss": 0.6885,
+      "step": 120
+    },
+    {
+      "epoch": 0.6313131313131313,
+      "grad_norm": 0.9520788192749023,
+      "learning_rate": 2.7990381056766583e-05,
+      "loss": 0.6744,
+      "step": 125
+    },
+    {
+      "epoch": 0.6565656565656566,
+      "grad_norm": 0.8425512909889221,
+      "learning_rate": 2.777648771814114e-05,
+      "loss": 0.6185,
+      "step": 130
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 0.929659903049469,
+      "learning_rate": 2.7552684578024e-05,
+      "loss": 0.5728,
+      "step": 135
+    },
+    {
+      "epoch": 0.7070707070707071,
+      "grad_norm": 0.8717391490936279,
+      "learning_rate": 2.7319145224394925e-05,
+      "loss": 0.604,
+      "step": 140
+    },
+    {
+      "epoch": 0.7323232323232324,
+      "grad_norm": 1.041341781616211,
+      "learning_rate": 2.7076050796913445e-05,
+      "loss": 0.5536,
+      "step": 145
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 0.9999323487281799,
+      "learning_rate": 2.6823589846421784e-05,
+      "loss": 0.5725,
+      "step": 150
+    },
+    {
+      "epoch": 0.7828282828282829,
+      "grad_norm": 0.9746265411376953,
+      "learning_rate": 2.6561958188699604e-05,
+      "loss": 0.5277,
+      "step": 155
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 1.0440582036972046,
+      "learning_rate": 2.6291358752583768e-05,
+      "loss": 0.5344,
+      "step": 160
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.9355345368385315,
+      "learning_rate": 2.6012001422571097e-05,
+      "loss": 0.5029,
+      "step": 165
+    },
+    {
+      "epoch": 0.8585858585858586,
+      "grad_norm": 1.1118171215057373,
+      "learning_rate": 2.5724102876026033e-05,
+      "loss": 0.4535,
+      "step": 170
+    },
+    {
+      "epoch": 0.8838383838383839,
+      "grad_norm": 1.0438495874404907,
+      "learning_rate": 2.5427886415119635e-05,
+      "loss": 0.4425,
+      "step": 175
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 1.1088472604751587,
+      "learning_rate": 2.5123581793630172e-05,
+      "loss": 0.4553,
+      "step": 180
+    },
+    {
+      "epoch": 0.9343434343434344,
+      "grad_norm": 1.105163812637329,
+      "learning_rate": 2.4811425038739634e-05,
+      "loss": 0.4163,
+      "step": 185
+    },
+    {
+      "epoch": 0.9595959595959596,
+      "grad_norm": 1.0986038446426392,
+      "learning_rate": 2.449165826796448e-05,
+      "loss": 0.425,
+      "step": 190
+    },
+    {
+      "epoch": 0.9848484848484849,
+      "grad_norm": 0.984187662601471,
+      "learning_rate": 2.416452950136248e-05,
+      "loss": 0.409,
+      "step": 195
+    },
+    {
+      "epoch": 1.0101010101010102,
+      "grad_norm": 1.0734666585922241,
+      "learning_rate": 2.3830292469161442e-05,
+      "loss": 0.3394,
+      "step": 200
+    },
+    {
+      "epoch": 1.0353535353535352,
+      "grad_norm": 1.0297268629074097,
+      "learning_rate": 2.348920641495893e-05,
+      "loss": 0.3812,
+      "step": 205
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 1.1269428730010986,
+      "learning_rate": 2.3141535894645677e-05,
+      "loss": 0.341,
+      "step": 210
+    },
+    {
+      "epoch": 1.0858585858585859,
+      "grad_norm": 1.075040578842163,
+      "learning_rate": 2.278755057120863e-05,
+      "loss": 0.3022,
+      "step": 215
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.8826611042022705,
+      "learning_rate": 2.2427525005572803e-05,
+      "loss": 0.2899,
+      "step": 220
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 0.988288164138794,
+      "learning_rate": 2.2061738443644124e-05,
+      "loss": 0.3029,
+      "step": 225
+    },
+    {
+      "epoch": 1.1616161616161615,
+      "grad_norm": 1.1140897274017334,
+      "learning_rate": 2.1690474599718487e-05,
+      "loss": 0.2812,
+      "step": 230
+    },
+    {
+      "epoch": 1.1868686868686869,
+      "grad_norm": 1.1010723114013672,
+      "learning_rate": 2.1314021436425026e-05,
+      "loss": 0.2711,
+      "step": 235
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 1.157459020614624,
+      "learning_rate": 2.0932670941374218e-05,
+      "loss": 0.2702,
+      "step": 240
+    },
+    {
+      "epoch": 1.2373737373737375,
+      "grad_norm": 1.2123245000839233,
+      "learning_rate": 2.054671890068414e-05,
+      "loss": 0.2505,
+      "step": 245
+    },
+    {
+      "epoch": 1.2626262626262625,
+      "grad_norm": 1.0079967975616455,
+      "learning_rate": 2.015646466956045e-05,
+      "loss": 0.2424,
+      "step": 250
+    },
+    {
+      "epoch": 1.2878787878787878,
+      "grad_norm": 1.3366535902023315,
+      "learning_rate": 1.976221094010814e-05,
+      "loss": 0.2422,
+      "step": 255
+    },
+    {
+      "epoch": 1.3131313131313131,
+      "grad_norm": 1.0681020021438599,
+      "learning_rate": 1.9364263506555043e-05,
+      "loss": 0.2319,
+      "step": 260
+    },
+    {
+      "epoch": 1.3383838383838385,
+      "grad_norm": 1.186680555343628,
+      "learning_rate": 1.8962931028069292e-05,
+      "loss": 0.2587,
+      "step": 265
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 1.150273323059082,
+      "learning_rate": 1.8558524789354606e-05,
+      "loss": 0.2377,
+      "step": 270
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.979213535785675,
+      "learning_rate": 1.8151358459209167e-05,
+      "loss": 0.1988,
+      "step": 275
+    },
+    {
+      "epoch": 1.4141414141414141,
+      "grad_norm": 1.0164731740951538,
+      "learning_rate": 1.7741747847235356e-05,
+      "loss": 0.1879,
+      "step": 280
+    },
+    {
+      "epoch": 1.4393939393939394,
+      "grad_norm": 1.1856359243392944,
+      "learning_rate": 1.7330010658888928e-05,
+      "loss": 0.2122,
+      "step": 285
+    },
+    {
+      "epoch": 1.4646464646464645,
+      "grad_norm": 1.0518406629562378,
+      "learning_rate": 1.69164662490578e-05,
+      "loss": 0.1981,
+      "step": 290
+    },
+    {
+      "epoch": 1.4898989898989898,
+      "grad_norm": 1.11225426197052,
+      "learning_rate": 1.6501435374361478e-05,
+      "loss": 0.1881,
+      "step": 295
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 1.0529050827026367,
+      "learning_rate": 1.6085239944363192e-05,
+      "loss": 0.1933,
+      "step": 300
+    },
+    {
+      "epoch": 1.5404040404040404,
+      "grad_norm": 1.2496590614318848,
+      "learning_rate": 1.5668202771887886e-05,
+      "loss": 0.1843,
+      "step": 305
+    },
+    {
+      "epoch": 1.5656565656565657,
+      "grad_norm": 1.2535083293914795,
+      "learning_rate": 1.5250647322639515e-05,
+      "loss": 0.1696,
+      "step": 310
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 0.9840067625045776,
+      "learning_rate": 1.4832897464312018e-05,
+      "loss": 0.1717,
+      "step": 315
+    },
+    {
+      "epoch": 1.6161616161616161,
+      "grad_norm": 1.0098856687545776,
+      "learning_rate": 1.4415277215388445e-05,
+      "loss": 0.1586,
+      "step": 320
+    },
+    {
+      "epoch": 1.6414141414141414,
+      "grad_norm": 1.0186234712600708,
+      "learning_rate": 1.3998110493823178e-05,
+      "loss": 0.1797,
+      "step": 325
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.8618770837783813,
+      "learning_rate": 1.3581720865802071e-05,
+      "loss": 0.1453,
+      "step": 330
+    },
+    {
+      "epoch": 1.691919191919192,
+      "grad_norm": 1.1810708045959473,
+      "learning_rate": 1.3166431294775487e-05,
+      "loss": 0.1461,
+      "step": 335
+    },
+    {
+      "epoch": 1.7171717171717171,
+      "grad_norm": 0.9822881817817688,
+      "learning_rate": 1.2752563890958778e-05,
+      "loss": 0.1408,
+      "step": 340
+    },
+    {
+      "epoch": 1.7424242424242424,
+      "grad_norm": 1.1187547445297241,
+      "learning_rate": 1.234043966149462e-05,
+      "loss": 0.1617,
+      "step": 345
+    },
+    {
+      "epoch": 1.7676767676767677,
+      "grad_norm": 0.8247243165969849,
+      "learning_rate": 1.1930378261470858e-05,
+      "loss": 0.146,
+      "step": 350
+    },
+    {
+      "epoch": 1.7929292929292928,
+      "grad_norm": 1.104274034500122,
+      "learning_rate": 1.1522697745987076e-05,
+      "loss": 0.1443,
+      "step": 355
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 1.0579862594604492,
+      "learning_rate": 1.1117714323462188e-05,
+      "loss": 0.1503,
+      "step": 360
+    },
+    {
+      "epoch": 1.8434343434343434,
+      "grad_norm": 0.9302670359611511,
+      "learning_rate": 1.0715742110374305e-05,
+      "loss": 0.1413,
+      "step": 365
+    },
+    {
+      "epoch": 1.8686868686868687,
+      "grad_norm": 0.9680148363113403,
+      "learning_rate": 1.0317092887623206e-05,
+      "loss": 0.123,
+      "step": 370
+    },
+    {
+      "epoch": 1.893939393939394,
+      "grad_norm": 0.8831433653831482,
+      "learning_rate": 9.922075858704368e-06,
+      "loss": 0.1335,
+      "step": 375
+    },
+    {
+      "epoch": 1.9191919191919191,
+      "grad_norm": 0.9100627899169922,
+      "learning_rate": 9.53099740988206e-06,
+      "loss": 0.1169,
+      "step": 380
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 1.0803728103637695,
+      "learning_rate": 9.144160872547579e-06,
+      "loss": 0.1072,
+      "step": 385
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 0.8936476111412048,
+      "learning_rate": 8.761866287946955e-06,
+      "loss": 0.101,
+      "step": 390
+    },
+    {
+      "epoch": 1.9949494949494948,
+      "grad_norm": 0.8314000368118286,
+      "learning_rate": 8.384410174460525e-06,
+      "loss": 0.1065,
+      "step": 395
+    },
+    {
+      "epoch": 2.0202020202020203,
+      "grad_norm": 0.7389856576919556,
+      "learning_rate": 8.012085297615027e-06,
+      "loss": 0.0865,
+      "step": 400
+    },
+    {
+      "epoch": 2.0454545454545454,
+      "grad_norm": 0.6313049793243408,
+      "learning_rate": 7.64518044300642e-06,
+      "loss": 0.0924,
+      "step": 405
+    },
+    {
+      "epoch": 2.0707070707070705,
+      "grad_norm": 0.7554161548614502,
+      "learning_rate": 7.2839801923096975e-06,
+      "loss": 0.087,
+      "step": 410
+    },
+    {
+      "epoch": 2.095959595959596,
+      "grad_norm": 0.5973594188690186,
+      "learning_rate": 6.928764702549411e-06,
+      "loss": 0.0837,
+      "step": 415
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 0.7747343182563782,
+      "learning_rate": 6.579809488801994e-06,
+      "loss": 0.0706,
+      "step": 420
+    },
+    {
+      "epoch": 2.1464646464646466,
+      "grad_norm": 0.8704163432121277,
+      "learning_rate": 6.237385210498588e-06,
+      "loss": 0.0817,
+      "step": 425
+    },
+    {
+      "epoch": 2.1717171717171717,
+      "grad_norm": 0.797909677028656,
+      "learning_rate": 5.901757461493989e-06,
+      "loss": 0.0871,
+      "step": 430
+    },
+    {
+      "epoch": 2.196969696969697,
+      "grad_norm": 0.6087777614593506,
+      "learning_rate": 5.573186564064649e-06,
+      "loss": 0.0819,
+      "step": 435
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.6898742318153381,
+      "learning_rate": 5.25192736699541e-06,
+      "loss": 0.081,
+      "step": 440
+    },
+    {
+      "epoch": 2.2474747474747474,
+      "grad_norm": 0.7056253552436829,
+      "learning_rate": 4.938229047911652e-06,
+      "loss": 0.0945,
+      "step": 445
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.6459508538246155,
+      "learning_rate": 4.6323349200101535e-06,
+      "loss": 0.0723,
+      "step": 450
+    },
+    {
+      "epoch": 2.297979797979798,
+      "grad_norm": 0.713525116443634,
+      "learning_rate": 4.334482243338589e-06,
+      "loss": 0.0703,
+      "step": 455
+    },
+    {
+      "epoch": 2.323232323232323,
+      "grad_norm": 0.74973064661026,
+      "learning_rate": 4.044902040769963e-06,
+      "loss": 0.0785,
+      "step": 460
+    },
+    {
+      "epoch": 2.3484848484848486,
+      "grad_norm": 0.7292476892471313,
+      "learning_rate": 3.7638189188148204e-06,
+      "loss": 0.0771,
+      "step": 465
+    },
+    {
+      "epoch": 2.3737373737373737,
+      "grad_norm": 0.7737451195716858,
+      "learning_rate": 3.491450893410134e-06,
+      "loss": 0.0746,
+      "step": 470
+    },
+    {
+      "epoch": 2.398989898989899,
+      "grad_norm": 0.7549379467964172,
+      "learning_rate": 3.2280092208200853e-06,
+      "loss": 0.0778,
+      "step": 475
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 0.8871992230415344,
+      "learning_rate": 2.9736982337797335e-06,
+      "loss": 0.0813,
+      "step": 480
+    },
+    {
+      "epoch": 2.4494949494949494,
+      "grad_norm": 0.5660616755485535,
+      "learning_rate": 2.728715183008864e-06,
+      "loss": 0.0652,
+      "step": 485
+    },
+    {
+      "epoch": 2.474747474747475,
+      "grad_norm": 0.6882954239845276,
+      "learning_rate": 2.4932500842187955e-06,
+      "loss": 0.0567,
+      "step": 490
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.5367974042892456,
+      "learning_rate": 2.267485570730894e-06,
+      "loss": 0.0663,
+      "step": 495
+    },
+    {
+      "epoch": 2.525252525252525,
+      "grad_norm": 0.6067714095115662,
+      "learning_rate": 2.0515967518210254e-06,
+      "loss": 0.0728,
+      "step": 500
+    },
+    {
+      "epoch": 2.5505050505050506,
+      "grad_norm": 0.5916219353675842,
+      "learning_rate": 1.8457510768999276e-06,
+      "loss": 0.0579,
+      "step": 505
+    },
+    {
+      "epoch": 2.5757575757575757,
+      "grad_norm": 0.5466343760490417,
+      "learning_rate": 1.6501082056347488e-06,
+      "loss": 0.0753,
+      "step": 510
+    },
+    {
+      "epoch": 2.601010101010101,
+      "grad_norm": 0.8206015825271606,
+      "learning_rate": 1.4648198841125453e-06,
+      "loss": 0.0729,
+      "step": 515
+    },
+    {
+      "epoch": 2.6262626262626263,
+      "grad_norm": 0.6055091619491577,
+      "learning_rate": 1.2900298271417592e-06,
+      "loss": 0.0701,
+      "step": 520
+    },
+    {
+      "epoch": 2.6515151515151514,
+      "grad_norm": 0.6920067667961121,
+      "learning_rate": 1.1258736067830016e-06,
+      "loss": 0.0577,
+      "step": 525
+    },
+    {
+      "epoch": 2.676767676767677,
+      "grad_norm": 0.6379139423370361,
+      "learning_rate": 9.724785471955566e-07,
+      "loss": 0.0689,
+      "step": 530
+    },
+    {
+      "epoch": 2.702020202020202,
+      "grad_norm": 0.7259097099304199,
+      "learning_rate": 8.299636258812199e-07,
+      "loss": 0.0739,
+      "step": 535
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.5183590054512024,
+      "learning_rate": 6.984393814019885e-07,
+      "loss": 0.0667,
+      "step": 540
+    },
+    {
+      "epoch": 2.7525252525252526,
+      "grad_norm": 0.5658006072044373,
+      "learning_rate": 5.780078276432865e-07,
+      "loss": 0.0719,
+      "step": 545
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.6104720234870911,
+      "learning_rate": 4.6876237468912007e-07,
+      "loss": 0.073,
+      "step": 550
+    },
+    {
+      "epoch": 2.8030303030303028,
+      "grad_norm": 0.4604014456272125,
+      "learning_rate": 3.707877563706158e-07,
+      "loss": 0.062,
+      "step": 555
+    },
+    {
+      "epoch": 2.8282828282828283,
+      "grad_norm": 0.721204400062561,
+      "learning_rate": 2.8415996454407287e-07,
+      "loss": 0.0765,
+      "step": 560
+    },
+    {
+      "epoch": 2.8535353535353534,
+      "grad_norm": 0.7024728059768677,
+      "learning_rate": 2.089461901495715e-07,
+      "loss": 0.0679,
+      "step": 565
+    },
+    {
+      "epoch": 2.878787878787879,
+      "grad_norm": 0.7194864749908447,
+      "learning_rate": 1.4520477109578712e-07,
+      "loss": 0.0601,
+      "step": 570
+    },
+    {
+      "epoch": 2.904040404040404,
+      "grad_norm": 0.46120721101760864,
+      "learning_rate": 9.298514701147898e-08,
+      "loss": 0.0589,
+      "step": 575
+    },
+    {
+      "epoch": 2.929292929292929,
+      "grad_norm": 0.5463808178901672,
+      "learning_rate": 5.232782089872601e-08,
+      "loss": 0.0582,
+      "step": 580
+    },
+    {
+      "epoch": 2.9545454545454546,
+      "grad_norm": 0.6010793447494507,
+      "learning_rate": 2.3264327717674728e-08,
+      "loss": 0.0717,
+      "step": 585
+    },
+    {
+      "epoch": 2.9797979797979797,
+      "grad_norm": 0.563383162021637,
+      "learning_rate": 5.817209927129752e-09,
+      "loss": 0.0662,
+      "step": 590
+    },
+    {
+      "epoch": 3.0,
+      "step": 594,
+      "total_flos": 8.274115317328773e+17,
+      "train_loss": 0.37865535192417377,
+      "train_runtime": 384.2891,
+      "train_samples_per_second": 49.447,
+      "train_steps_per_second": 1.546
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 594,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 20000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.274115317328773e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

102_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d00cb6bfe60ac19c3ad258ecdb3b6add2bd95f5518cfbec45963828d26efbea
+size 8273