Upload folder using huggingface_hub

11_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": [
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

11_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b1792c7665ef3e4df6524704fde5814607b912d12efa80be920957a5b456ee
+size 791751704

11_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
+}

11_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.6555905027177185e+18,
+    "train_loss": 0.5416349868819188,
+    "train_runtime": 801.1996,
+    "train_samples": 11340,
+    "train_samples_per_second": 42.461,
+    "train_steps_per_second": 1.329
+}

11_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 %}

11_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
+}

11_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
+  }
+}

11_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
+}

11_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.6555905027177185e+18,
+    "train_loss": 0.5416349868819188,
+    "train_runtime": 801.1996,
+    "train_samples": 11340,
+    "train_samples_per_second": 42.461,
+    "train_steps_per_second": 1.329
+}

11_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1065,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014104372355430184,
+      "grad_norm": 3.4026665687561035,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.5486,
+      "step": 5
+    },
+    {
+      "epoch": 0.028208744710860368,
+      "grad_norm": 2.145953416824341,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 1.4458,
+      "step": 10
+    },
+    {
+      "epoch": 0.04231311706629055,
+      "grad_norm": 0.7927170991897583,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 1.4446,
+      "step": 15
+    },
+    {
+      "epoch": 0.056417489421720736,
+      "grad_norm": 0.5019737482070923,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 1.2759,
+      "step": 20
+    },
+    {
+      "epoch": 0.07052186177715092,
+      "grad_norm": 0.3727194666862488,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.2311,
+      "step": 25
+    },
+    {
+      "epoch": 0.0846262341325811,
+      "grad_norm": 0.354473739862442,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 1.2435,
+      "step": 30
+    },
+    {
+      "epoch": 0.09873060648801128,
+      "grad_norm": 0.3713827133178711,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 1.2071,
+      "step": 35
+    },
+    {
+      "epoch": 0.11283497884344147,
+      "grad_norm": 0.4175741970539093,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 1.2358,
+      "step": 40
+    },
+    {
+      "epoch": 0.12693935119887165,
+      "grad_norm": 0.3433670699596405,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 1.1979,
+      "step": 45
+    },
+    {
+      "epoch": 0.14104372355430184,
+      "grad_norm": 0.3494504988193512,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 1.1773,
+      "step": 50
+    },
+    {
+      "epoch": 0.15514809590973203,
+      "grad_norm": 0.3510345220565796,
+      "learning_rate": 3e-05,
+      "loss": 1.1349,
+      "step": 55
+    },
+    {
+      "epoch": 0.1692524682651622,
+      "grad_norm": 0.3901633024215698,
+      "learning_rate": 2.999818953568259e-05,
+      "loss": 1.1622,
+      "step": 60
+    },
+    {
+      "epoch": 0.18335684062059238,
+      "grad_norm": 0.33558905124664307,
+      "learning_rate": 2.9992758579767835e-05,
+      "loss": 1.1304,
+      "step": 65
+    },
+    {
+      "epoch": 0.19746121297602257,
+      "grad_norm": 0.4059647023677826,
+      "learning_rate": 2.9983708443262656e-05,
+      "loss": 1.1509,
+      "step": 70
+    },
+    {
+      "epoch": 0.21156558533145275,
+      "grad_norm": 0.3643777668476105,
+      "learning_rate": 2.9971041310826943e-05,
+      "loss": 1.1312,
+      "step": 75
+    },
+    {
+      "epoch": 0.22566995768688294,
+      "grad_norm": 0.39006516337394714,
+      "learning_rate": 2.99547602402462e-05,
+      "loss": 1.1063,
+      "step": 80
+    },
+    {
+      "epoch": 0.2397743300423131,
+      "grad_norm": 0.425136923789978,
+      "learning_rate": 2.993486916169341e-05,
+      "loss": 1.0511,
+      "step": 85
+    },
+    {
+      "epoch": 0.2538787023977433,
+      "grad_norm": 0.3901968002319336,
+      "learning_rate": 2.9911372876780297e-05,
+      "loss": 1.0678,
+      "step": 90
+    },
+    {
+      "epoch": 0.2679830747531735,
+      "grad_norm": 0.38757896423339844,
+      "learning_rate": 2.988427705739825e-05,
+      "loss": 1.0773,
+      "step": 95
+    },
+    {
+      "epoch": 0.2820874471086037,
+      "grad_norm": 0.4275025427341461,
+      "learning_rate": 2.985358824434916e-05,
+      "loss": 1.0376,
+      "step": 100
+    },
+    {
+      "epoch": 0.29619181946403383,
+      "grad_norm": 0.467244952917099,
+      "learning_rate": 2.9819313845766484e-05,
+      "loss": 0.9868,
+      "step": 105
+    },
+    {
+      "epoch": 0.31029619181946405,
+      "grad_norm": 0.5277608036994934,
+      "learning_rate": 2.978146213532697e-05,
+      "loss": 1.0285,
+      "step": 110
+    },
+    {
+      "epoch": 0.3244005641748942,
+      "grad_norm": 0.4208105206489563,
+      "learning_rate": 2.9740042250253443e-05,
+      "loss": 1.0321,
+      "step": 115
+    },
+    {
+      "epoch": 0.3385049365303244,
+      "grad_norm": 0.49172303080558777,
+      "learning_rate": 2.969506418910909e-05,
+      "loss": 0.9948,
+      "step": 120
+    },
+    {
+      "epoch": 0.3526093088857546,
+      "grad_norm": 0.4646231532096863,
+      "learning_rate": 2.9646538809383876e-05,
+      "loss": 0.9977,
+      "step": 125
+    },
+    {
+      "epoch": 0.36671368124118475,
+      "grad_norm": 0.5360001921653748,
+      "learning_rate": 2.959447782487361e-05,
+      "loss": 0.991,
+      "step": 130
+    },
+    {
+      "epoch": 0.38081805359661497,
+      "grad_norm": 0.4593433737754822,
+      "learning_rate": 2.9538893802852254e-05,
+      "loss": 0.9335,
+      "step": 135
+    },
+    {
+      "epoch": 0.39492242595204513,
+      "grad_norm": 0.5145832896232605,
+      "learning_rate": 2.947980016103828e-05,
+      "loss": 0.9756,
+      "step": 140
+    },
+    {
+      "epoch": 0.4090267983074753,
+      "grad_norm": 0.5019190311431885,
+      "learning_rate": 2.9417211164355668e-05,
+      "loss": 1.0048,
+      "step": 145
+    },
+    {
+      "epoch": 0.4231311706629055,
+      "grad_norm": 0.5391433238983154,
+      "learning_rate": 2.9351141921490436e-05,
+      "loss": 0.9798,
+      "step": 150
+    },
+    {
+      "epoch": 0.43723554301833567,
+      "grad_norm": 0.6211673617362976,
+      "learning_rate": 2.9281608381243485e-05,
+      "loss": 0.8636,
+      "step": 155
+    },
+    {
+      "epoch": 0.4513399153737659,
+      "grad_norm": 0.5945197939872742,
+      "learning_rate": 2.92086273286806e-05,
+      "loss": 0.9093,
+      "step": 160
+    },
+    {
+      "epoch": 0.46544428772919605,
+      "grad_norm": 0.6164790391921997,
+      "learning_rate": 2.9132216381080664e-05,
+      "loss": 0.8731,
+      "step": 165
+    },
+    {
+      "epoch": 0.4795486600846262,
+      "grad_norm": 0.5757480263710022,
+      "learning_rate": 2.9052393983682876e-05,
+      "loss": 0.8949,
+      "step": 170
+    },
+    {
+      "epoch": 0.4936530324400564,
+      "grad_norm": 0.5886030793190002,
+      "learning_rate": 2.8969179405234202e-05,
+      "loss": 0.8976,
+      "step": 175
+    },
+    {
+      "epoch": 0.5077574047954866,
+      "grad_norm": 0.67991042137146,
+      "learning_rate": 2.888259273333798e-05,
+      "loss": 0.9262,
+      "step": 180
+    },
+    {
+      "epoch": 0.5218617771509168,
+      "grad_norm": 0.6034244894981384,
+      "learning_rate": 2.8792654869604844e-05,
+      "loss": 0.89,
+      "step": 185
+    },
+    {
+      "epoch": 0.535966149506347,
+      "grad_norm": 0.664543628692627,
+      "learning_rate": 2.8699387524607206e-05,
+      "loss": 0.9118,
+      "step": 190
+    },
+    {
+      "epoch": 0.5500705218617772,
+      "grad_norm": 0.7276310920715332,
+      "learning_rate": 2.8602813212638415e-05,
+      "loss": 0.8443,
+      "step": 195
+    },
+    {
+      "epoch": 0.5641748942172073,
+      "grad_norm": 0.6345068216323853,
+      "learning_rate": 2.8502955246277904e-05,
+      "loss": 0.8223,
+      "step": 200
+    },
+    {
+      "epoch": 0.5782792665726375,
+      "grad_norm": 0.6952701210975647,
+      "learning_rate": 2.839983773076367e-05,
+      "loss": 0.8894,
+      "step": 205
+    },
+    {
+      "epoch": 0.5923836389280677,
+      "grad_norm": 0.6775036454200745,
+      "learning_rate": 2.8293485558173352e-05,
+      "loss": 0.8426,
+      "step": 210
+    },
+    {
+      "epoch": 0.6064880112834978,
+      "grad_norm": 0.6735378503799438,
+      "learning_rate": 2.8183924401415424e-05,
+      "loss": 0.7859,
+      "step": 215
+    },
+    {
+      "epoch": 0.6205923836389281,
+      "grad_norm": 0.7856212854385376,
+      "learning_rate": 2.8071180708031874e-05,
+      "loss": 0.813,
+      "step": 220
+    },
+    {
+      "epoch": 0.6346967559943583,
+      "grad_norm": 0.7166884541511536,
+      "learning_rate": 2.7955281693813884e-05,
+      "loss": 0.7976,
+      "step": 225
+    },
+    {
+      "epoch": 0.6488011283497884,
+      "grad_norm": 0.7462570667266846,
+      "learning_rate": 2.7836255336232076e-05,
+      "loss": 0.8424,
+      "step": 230
+    },
+    {
+      "epoch": 0.6629055007052186,
+      "grad_norm": 0.8340402245521545,
+      "learning_rate": 2.771413036768288e-05,
+      "loss": 0.7629,
+      "step": 235
+    },
+    {
+      "epoch": 0.6770098730606487,
+      "grad_norm": 0.7492517232894897,
+      "learning_rate": 2.7588936268552675e-05,
+      "loss": 0.771,
+      "step": 240
+    },
+    {
+      "epoch": 0.691114245416079,
+      "grad_norm": 0.7002833485603333,
+      "learning_rate": 2.7460703260101352e-05,
+      "loss": 0.737,
+      "step": 245
+    },
+    {
+      "epoch": 0.7052186177715092,
+      "grad_norm": 0.7530421018600464,
+      "learning_rate": 2.732946229716707e-05,
+      "loss": 0.8401,
+      "step": 250
+    },
+    {
+      "epoch": 0.7193229901269393,
+      "grad_norm": 0.7170169353485107,
+      "learning_rate": 2.7195245060693875e-05,
+      "loss": 0.7719,
+      "step": 255
+    },
+    {
+      "epoch": 0.7334273624823695,
+      "grad_norm": 0.8507378697395325,
+      "learning_rate": 2.7058083950084078e-05,
+      "loss": 0.7618,
+      "step": 260
+    },
+    {
+      "epoch": 0.7475317348377997,
+      "grad_norm": 0.7342758774757385,
+      "learning_rate": 2.6918012075377226e-05,
+      "loss": 0.7348,
+      "step": 265
+    },
+    {
+      "epoch": 0.7616361071932299,
+      "grad_norm": 0.7930523157119751,
+      "learning_rate": 2.6775063249257455e-05,
+      "loss": 0.734,
+      "step": 270
+    },
+    {
+      "epoch": 0.7757404795486601,
+      "grad_norm": 0.8301742076873779,
+      "learning_rate": 2.6629271978891274e-05,
+      "loss": 0.7065,
+      "step": 275
+    },
+    {
+      "epoch": 0.7898448519040903,
+      "grad_norm": 0.7755118608474731,
+      "learning_rate": 2.6480673457597737e-05,
+      "loss": 0.7547,
+      "step": 280
+    },
+    {
+      "epoch": 0.8039492242595204,
+      "grad_norm": 0.8562586903572083,
+      "learning_rate": 2.6329303556352887e-05,
+      "loss": 0.6927,
+      "step": 285
+    },
+    {
+      "epoch": 0.8180535966149506,
+      "grad_norm": 0.9069969058036804,
+      "learning_rate": 2.617519881513072e-05,
+      "loss": 0.6915,
+      "step": 290
+    },
+    {
+      "epoch": 0.8321579689703809,
+      "grad_norm": 0.7898303270339966,
+      "learning_rate": 2.601839643408259e-05,
+      "loss": 0.7254,
+      "step": 295
+    },
+    {
+      "epoch": 0.846262341325811,
+      "grad_norm": 0.7645297646522522,
+      "learning_rate": 2.585893426455726e-05,
+      "loss": 0.6906,
+      "step": 300
+    },
+    {
+      "epoch": 0.8603667136812412,
+      "grad_norm": 0.850929856300354,
+      "learning_rate": 2.569685079996379e-05,
+      "loss": 0.7268,
+      "step": 305
+    },
+    {
+      "epoch": 0.8744710860366713,
+      "grad_norm": 0.7832868099212646,
+      "learning_rate": 2.553218516647939e-05,
+      "loss": 0.6949,
+      "step": 310
+    },
+    {
+      "epoch": 0.8885754583921015,
+      "grad_norm": 0.8477210998535156,
+      "learning_rate": 2.5364977113604556e-05,
+      "loss": 0.6809,
+      "step": 315
+    },
+    {
+      "epoch": 0.9026798307475318,
+      "grad_norm": 0.9933244585990906,
+      "learning_rate": 2.5195267004567726e-05,
+      "loss": 0.6936,
+      "step": 320
+    },
+    {
+      "epoch": 0.9167842031029619,
+      "grad_norm": 0.8580759167671204,
+      "learning_rate": 2.5023095806581802e-05,
+      "loss": 0.6376,
+      "step": 325
+    },
+    {
+      "epoch": 0.9308885754583921,
+      "grad_norm": 0.8906660676002502,
+      "learning_rate": 2.4848505080954837e-05,
+      "loss": 0.6418,
+      "step": 330
+    },
+    {
+      "epoch": 0.9449929478138223,
+      "grad_norm": 0.9870065450668335,
+      "learning_rate": 2.4671536973057353e-05,
+      "loss": 0.6319,
+      "step": 335
+    },
+    {
+      "epoch": 0.9590973201692524,
+      "grad_norm": 0.8756622672080994,
+      "learning_rate": 2.4492234202148643e-05,
+      "loss": 0.6461,
+      "step": 340
+    },
+    {
+      "epoch": 0.9732016925246827,
+      "grad_norm": 0.9434117674827576,
+      "learning_rate": 2.431064005106453e-05,
+      "loss": 0.6639,
+      "step": 345
+    },
+    {
+      "epoch": 0.9873060648801129,
+      "grad_norm": 1.0191916227340698,
+      "learning_rate": 2.4126798355769127e-05,
+      "loss": 0.6703,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1471611261367798,
+      "learning_rate": 2.394075349477302e-05,
+      "loss": 0.6511,
+      "step": 355
+    },
+    {
+      "epoch": 1.0141043723554302,
+      "grad_norm": 0.882536768913269,
+      "learning_rate": 2.3752550378420504e-05,
+      "loss": 0.5488,
+      "step": 360
+    },
+    {
+      "epoch": 1.0282087447108603,
+      "grad_norm": 1.0113587379455566,
+      "learning_rate": 2.356223443804846e-05,
+      "loss": 0.5527,
+      "step": 365
+    },
+    {
+      "epoch": 1.0423131170662905,
+      "grad_norm": 0.9070690870285034,
+      "learning_rate": 2.3369851615019436e-05,
+      "loss": 0.5291,
+      "step": 370
+    },
+    {
+      "epoch": 1.0564174894217206,
+      "grad_norm": 0.9254192113876343,
+      "learning_rate": 2.3175448349631612e-05,
+      "loss": 0.5092,
+      "step": 375
+    },
+    {
+      "epoch": 1.0705218617771508,
+      "grad_norm": 0.8938282132148743,
+      "learning_rate": 2.297907156990834e-05,
+      "loss": 0.5213,
+      "step": 380
+    },
+    {
+      "epoch": 1.0846262341325812,
+      "grad_norm": 1.0098944902420044,
+      "learning_rate": 2.278076868026995e-05,
+      "loss": 0.5389,
+      "step": 385
+    },
+    {
+      "epoch": 1.0987306064880114,
+      "grad_norm": 0.8761587142944336,
+      "learning_rate": 2.2580587550090545e-05,
+      "loss": 0.5356,
+      "step": 390
+    },
+    {
+      "epoch": 1.1128349788434415,
+      "grad_norm": 0.9284277558326721,
+      "learning_rate": 2.237857650214255e-05,
+      "loss": 0.485,
+      "step": 395
+    },
+    {
+      "epoch": 1.1269393511988717,
+      "grad_norm": 0.9418231844902039,
+      "learning_rate": 2.217478430093183e-05,
+      "loss": 0.544,
+      "step": 400
+    },
+    {
+      "epoch": 1.1410437235543018,
+      "grad_norm": 0.975740909576416,
+      "learning_rate": 2.1969260140926184e-05,
+      "loss": 0.4945,
+      "step": 405
+    },
+    {
+      "epoch": 1.155148095909732,
+      "grad_norm": 0.9024131298065186,
+      "learning_rate": 2.1762053634680027e-05,
+      "loss": 0.5342,
+      "step": 410
+    },
+    {
+      "epoch": 1.1692524682651622,
+      "grad_norm": 1.0473675727844238,
+      "learning_rate": 2.155321480085813e-05,
+      "loss": 0.4725,
+      "step": 415
+    },
+    {
+      "epoch": 1.1833568406205923,
+      "grad_norm": 0.8896573781967163,
+      "learning_rate": 2.13427940521614e-05,
+      "loss": 0.4854,
+      "step": 420
+    },
+    {
+      "epoch": 1.1974612129760225,
+      "grad_norm": 0.9557392597198486,
+      "learning_rate": 2.1130842183157454e-05,
+      "loss": 0.4804,
+      "step": 425
+    },
+    {
+      "epoch": 1.2115655853314529,
+      "grad_norm": 1.0007184743881226,
+      "learning_rate": 2.0917410358019073e-05,
+      "loss": 0.4924,
+      "step": 430
+    },
+    {
+      "epoch": 1.225669957686883,
+      "grad_norm": 1.0220506191253662,
+      "learning_rate": 2.07025500981734e-05,
+      "loss": 0.501,
+      "step": 435
+    },
+    {
+      "epoch": 1.2397743300423132,
+      "grad_norm": 1.111889123916626,
+      "learning_rate": 2.0486313269864934e-05,
+      "loss": 0.4883,
+      "step": 440
+    },
+    {
+      "epoch": 1.2538787023977433,
+      "grad_norm": 0.8829588890075684,
+      "learning_rate": 2.0268752071635233e-05,
+      "loss": 0.4881,
+      "step": 445
+    },
+    {
+      "epoch": 1.2679830747531735,
+      "grad_norm": 1.1053252220153809,
+      "learning_rate": 2.004991902172248e-05,
+      "loss": 0.5056,
+      "step": 450
+    },
+    {
+      "epoch": 1.2820874471086037,
+      "grad_norm": 0.993268609046936,
+      "learning_rate": 1.9829866945383767e-05,
+      "loss": 0.4962,
+      "step": 455
+    },
+    {
+      "epoch": 1.2961918194640338,
+      "grad_norm": 1.0805367231369019,
+      "learning_rate": 1.9608648962143395e-05,
+      "loss": 0.4869,
+      "step": 460
+    },
+    {
+      "epoch": 1.310296191819464,
+      "grad_norm": 0.8731850981712341,
+      "learning_rate": 1.938631847297004e-05,
+      "loss": 0.471,
+      "step": 465
+    },
+    {
+      "epoch": 1.3244005641748942,
+      "grad_norm": 0.8949744701385498,
+      "learning_rate": 1.9162929147385995e-05,
+      "loss": 0.4546,
+      "step": 470
+    },
+    {
+      "epoch": 1.3385049365303243,
+      "grad_norm": 0.9245812892913818,
+      "learning_rate": 1.893853491051165e-05,
+      "loss": 0.4803,
+      "step": 475
+    },
+    {
+      "epoch": 1.3526093088857545,
+      "grad_norm": 1.0126726627349854,
+      "learning_rate": 1.8713189930048196e-05,
+      "loss": 0.4569,
+      "step": 480
+    },
+    {
+      "epoch": 1.3667136812411846,
+      "grad_norm": 1.0559196472167969,
+      "learning_rate": 1.84869486032018e-05,
+      "loss": 0.4746,
+      "step": 485
+    },
+    {
+      "epoch": 1.380818053596615,
+      "grad_norm": 0.9784413576126099,
+      "learning_rate": 1.825986554355236e-05,
+      "loss": 0.4666,
+      "step": 490
+    },
+    {
+      "epoch": 1.3949224259520452,
+      "grad_norm": 0.9925135970115662,
+      "learning_rate": 1.8031995567870108e-05,
+      "loss": 0.4764,
+      "step": 495
+    },
+    {
+      "epoch": 1.4090267983074753,
+      "grad_norm": 0.9366908669471741,
+      "learning_rate": 1.7803393682883028e-05,
+      "loss": 0.4812,
+      "step": 500
+    },
+    {
+      "epoch": 1.4231311706629055,
+      "grad_norm": 1.09544837474823,
+      "learning_rate": 1.757411507199855e-05,
+      "loss": 0.4697,
+      "step": 505
+    },
+    {
+      "epoch": 1.4372355430183357,
+      "grad_norm": 1.006853461265564,
+      "learning_rate": 1.7344215081982503e-05,
+      "loss": 0.4479,
+      "step": 510
+    },
+    {
+      "epoch": 1.4513399153737658,
+      "grad_norm": 1.1112549304962158,
+      "learning_rate": 1.7113749209598685e-05,
+      "loss": 0.424,
+      "step": 515
+    },
+    {
+      "epoch": 1.465444287729196,
+      "grad_norm": 0.9928213357925415,
+      "learning_rate": 1.6882773088212213e-05,
+      "loss": 0.4067,
+      "step": 520
+    },
+    {
+      "epoch": 1.4795486600846262,
+      "grad_norm": 1.0899250507354736,
+      "learning_rate": 1.6651342474359876e-05,
+      "loss": 0.4011,
+      "step": 525
+    },
+    {
+      "epoch": 1.4936530324400565,
+      "grad_norm": 0.9399552345275879,
+      "learning_rate": 1.6419513234290787e-05,
+      "loss": 0.4729,
+      "step": 530
+    },
+    {
+      "epoch": 1.5077574047954867,
+      "grad_norm": 1.066135287284851,
+      "learning_rate": 1.618734133048052e-05,
+      "loss": 0.4386,
+      "step": 535
+    },
+    {
+      "epoch": 1.5218617771509169,
+      "grad_norm": 1.0943255424499512,
+      "learning_rate": 1.5954882808122076e-05,
+      "loss": 0.4272,
+      "step": 540
+    },
+    {
+      "epoch": 1.535966149506347,
+      "grad_norm": 1.063990592956543,
+      "learning_rate": 1.572219378159677e-05,
+      "loss": 0.4524,
+      "step": 545
+    },
+    {
+      "epoch": 1.5500705218617772,
+      "grad_norm": 1.1298741102218628,
+      "learning_rate": 1.5489330420928554e-05,
+      "loss": 0.4221,
+      "step": 550
+    },
+    {
+      "epoch": 1.5641748942172073,
+      "grad_norm": 1.0070699453353882,
+      "learning_rate": 1.52563489382248e-05,
+      "loss": 0.4055,
+      "step": 555
+    },
+    {
+      "epoch": 1.5782792665726375,
+      "grad_norm": 1.1053661108016968,
+      "learning_rate": 1.502330557410699e-05,
+      "loss": 0.4082,
+      "step": 560
+    },
+    {
+      "epoch": 1.5923836389280677,
+      "grad_norm": 1.0855764150619507,
+      "learning_rate": 1.4790256584134467e-05,
+      "loss": 0.4309,
+      "step": 565
+    },
+    {
+      "epoch": 1.6064880112834978,
+      "grad_norm": 1.0602757930755615,
+      "learning_rate": 1.4557258225224645e-05,
+      "loss": 0.4146,
+      "step": 570
+    },
+    {
+      "epoch": 1.620592383638928,
+      "grad_norm": 0.98285973072052,
+      "learning_rate": 1.4324366742072829e-05,
+      "loss": 0.437,
+      "step": 575
+    },
+    {
+      "epoch": 1.6346967559943582,
+      "grad_norm": 1.2043741941452026,
+      "learning_rate": 1.4091638353575025e-05,
+      "loss": 0.369,
+      "step": 580
+    },
+    {
+      "epoch": 1.6488011283497883,
+      "grad_norm": 1.0864444971084595,
+      "learning_rate": 1.3859129239256979e-05,
+      "loss": 0.4178,
+      "step": 585
+    },
+    {
+      "epoch": 1.6629055007052185,
+      "grad_norm": 1.0565195083618164,
+      "learning_rate": 1.3626895525712684e-05,
+      "loss": 0.4569,
+      "step": 590
+    },
+    {
+      "epoch": 1.6770098730606486,
+      "grad_norm": 0.9216626882553101,
+      "learning_rate": 1.339499327305569e-05,
+      "loss": 0.4332,
+      "step": 595
+    },
+    {
+      "epoch": 1.691114245416079,
+      "grad_norm": 1.0148590803146362,
+      "learning_rate": 1.3163478461386473e-05,
+      "loss": 0.4191,
+      "step": 600
+    },
+    {
+      "epoch": 1.7052186177715092,
+      "grad_norm": 1.1015889644622803,
+      "learning_rate": 1.2932406977279098e-05,
+      "loss": 0.382,
+      "step": 605
+    },
+    {
+      "epoch": 1.7193229901269393,
+      "grad_norm": 1.029260277748108,
+      "learning_rate": 1.2701834600290465e-05,
+      "loss": 0.3889,
+      "step": 610
+    },
+    {
+      "epoch": 1.7334273624823695,
+      "grad_norm": 1.2686400413513184,
+      "learning_rate": 1.2471816989495388e-05,
+      "loss": 0.4136,
+      "step": 615
+    },
+    {
+      "epoch": 1.7475317348377997,
+      "grad_norm": 1.0710433721542358,
+      "learning_rate": 1.224240967005076e-05,
+      "loss": 0.3611,
+      "step": 620
+    },
+    {
+      "epoch": 1.76163610719323,
+      "grad_norm": 1.0217320919036865,
+      "learning_rate": 1.2013668019792059e-05,
+      "loss": 0.3827,
+      "step": 625
+    },
+    {
+      "epoch": 1.7757404795486602,
+      "grad_norm": 0.9862416982650757,
+      "learning_rate": 1.178564725586537e-05,
+      "loss": 0.3826,
+      "step": 630
+    },
+    {
+      "epoch": 1.7898448519040904,
+      "grad_norm": 1.0525702238082886,
+      "learning_rate": 1.155840242139826e-05,
+      "loss": 0.3585,
+      "step": 635
+    },
+    {
+      "epoch": 1.8039492242595205,
+      "grad_norm": 1.1119732856750488,
+      "learning_rate": 1.1331988372212604e-05,
+      "loss": 0.4116,
+      "step": 640
+    },
+    {
+      "epoch": 1.8180535966149507,
+      "grad_norm": 1.1011879444122314,
+      "learning_rate": 1.1106459763582677e-05,
+      "loss": 0.4135,
+      "step": 645
+    },
+    {
+      "epoch": 1.8321579689703809,
+      "grad_norm": 1.0232272148132324,
+      "learning_rate": 1.0881871037041609e-05,
+      "loss": 0.3998,
+      "step": 650
+    },
+    {
+      "epoch": 1.846262341325811,
+      "grad_norm": 0.9756852984428406,
+      "learning_rate": 1.0658276407239462e-05,
+      "loss": 0.3555,
+      "step": 655
+    },
+    {
+      "epoch": 1.8603667136812412,
+      "grad_norm": 1.0950740575790405,
+      "learning_rate": 1.0435729848856076e-05,
+      "loss": 0.3633,
+      "step": 660
+    },
+    {
+      "epoch": 1.8744710860366713,
+      "grad_norm": 1.022698998451233,
+      "learning_rate": 1.0214285083571852e-05,
+      "loss": 0.3422,
+      "step": 665
+    },
+    {
+      "epoch": 1.8885754583921015,
+      "grad_norm": 0.9492419362068176,
+      "learning_rate": 9.993995567099557e-06,
+      "loss": 0.4003,
+      "step": 670
+    },
+    {
+      "epoch": 1.9026798307475317,
+      "grad_norm": 1.1028763055801392,
+      "learning_rate": 9.774914476280406e-06,
+      "loss": 0.4064,
+      "step": 675
+    },
+    {
+      "epoch": 1.9167842031029618,
+      "grad_norm": 1.0520737171173096,
+      "learning_rate": 9.5570946962474e-06,
+      "loss": 0.3389,
+      "step": 680
+    },
+    {
+      "epoch": 1.930888575458392,
+      "grad_norm": 1.1387090682983398,
+      "learning_rate": 9.340588807659128e-06,
+      "loss": 0.3264,
+      "step": 685
+    },
+    {
+      "epoch": 1.9449929478138221,
+      "grad_norm": 1.1008509397506714,
+      "learning_rate": 9.125449074007022e-06,
+      "loss": 0.3735,
+      "step": 690
+    },
+    {
+      "epoch": 1.9590973201692523,
+      "grad_norm": 1.0661132335662842,
+      "learning_rate": 8.911727428999228e-06,
+      "loss": 0.3433,
+      "step": 695
+    },
+    {
+      "epoch": 1.9732016925246827,
+      "grad_norm": 1.0329855680465698,
+      "learning_rate": 8.699475464024022e-06,
+      "loss": 0.3608,
+      "step": 700
+    },
+    {
+      "epoch": 1.9873060648801129,
+      "grad_norm": 1.0337284803390503,
+      "learning_rate": 8.488744415695935e-06,
+      "loss": 0.3405,
+      "step": 705
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4545073509216309,
+      "learning_rate": 8.279585153487432e-06,
+      "loss": 0.3404,
+      "step": 710
+    },
+    {
+      "epoch": 2.01410437235543,
+      "grad_norm": 1.0898131132125854,
+      "learning_rate": 8.072048167449306e-06,
+      "loss": 0.2923,
+      "step": 715
+    },
+    {
+      "epoch": 2.0282087447108603,
+      "grad_norm": 1.0214054584503174,
+      "learning_rate": 7.866183556022589e-06,
+      "loss": 0.2912,
+      "step": 720
+    },
+    {
+      "epoch": 2.0423131170662905,
+      "grad_norm": 1.0093437433242798,
+      "learning_rate": 7.66204101394504e-06,
+      "loss": 0.259,
+      "step": 725
+    },
+    {
+      "epoch": 2.0564174894217206,
+      "grad_norm": 1.044844627380371,
+      "learning_rate": 7.459669820255068e-06,
+      "loss": 0.2693,
+      "step": 730
+    },
+    {
+      "epoch": 2.070521861777151,
+      "grad_norm": 1.1461502313613892,
+      "learning_rate": 7.259118826396023e-06,
+      "loss": 0.2865,
+      "step": 735
+    },
+    {
+      "epoch": 2.084626234132581,
+      "grad_norm": 1.0759320259094238,
+      "learning_rate": 7.060436444423655e-06,
+      "loss": 0.3049,
+      "step": 740
+    },
+    {
+      "epoch": 2.098730606488011,
+      "grad_norm": 1.0399717092514038,
+      "learning_rate": 6.863670635319715e-06,
+      "loss": 0.2694,
+      "step": 745
+    },
+    {
+      "epoch": 2.1128349788434413,
+      "grad_norm": 1.14724862575531,
+      "learning_rate": 6.668868897414361e-06,
+      "loss": 0.2862,
+      "step": 750
+    },
+    {
+      "epoch": 2.1269393511988715,
+      "grad_norm": 1.1007517576217651,
+      "learning_rate": 6.476078254920332e-06,
+      "loss": 0.3103,
+      "step": 755
+    },
+    {
+      "epoch": 2.1410437235543016,
+      "grad_norm": 1.1657521724700928,
+      "learning_rate": 6.285345246581483e-06,
+      "loss": 0.2605,
+      "step": 760
+    },
+    {
+      "epoch": 2.155148095909732,
+      "grad_norm": 1.06886625289917,
+      "learning_rate": 6.096715914438581e-06,
+      "loss": 0.2849,
+      "step": 765
+    },
+    {
+      "epoch": 2.1692524682651624,
+      "grad_norm": 1.0467849969863892,
+      "learning_rate": 5.9102357927149636e-06,
+      "loss": 0.2661,
+      "step": 770
+    },
+    {
+      "epoch": 2.1833568406205925,
+      "grad_norm": 1.0040737390518188,
+      "learning_rate": 5.725949896824805e-06,
+      "loss": 0.2626,
+      "step": 775
+    },
+    {
+      "epoch": 2.1974612129760227,
+      "grad_norm": 1.3097790479660034,
+      "learning_rate": 5.543902712506608e-06,
+      "loss": 0.2583,
+      "step": 780
+    },
+    {
+      "epoch": 2.211565585331453,
+      "grad_norm": 1.1528080701828003,
+      "learning_rate": 5.364138185084537e-06,
+      "loss": 0.256,
+      "step": 785
+    },
+    {
+      "epoch": 2.225669957686883,
+      "grad_norm": 1.1419826745986938,
+      "learning_rate": 5.186699708860253e-06,
+      "loss": 0.2799,
+      "step": 790
+    },
+    {
+      "epoch": 2.239774330042313,
+      "grad_norm": 1.1660910844802856,
+      "learning_rate": 5.011630116637714e-06,
+      "loss": 0.2611,
+      "step": 795
+    },
+    {
+      "epoch": 2.2538787023977433,
+      "grad_norm": 1.0248594284057617,
+      "learning_rate": 4.838971669383567e-06,
+      "loss": 0.248,
+      "step": 800
+    },
+    {
+      "epoch": 2.2679830747531735,
+      "grad_norm": 0.9512549638748169,
+      "learning_rate": 4.668766046025522e-06,
+      "loss": 0.2737,
+      "step": 805
+    },
+    {
+      "epoch": 2.2820874471086037,
+      "grad_norm": 1.1646984815597534,
+      "learning_rate": 4.501054333391275e-06,
+      "loss": 0.2696,
+      "step": 810
+    },
+    {
+      "epoch": 2.296191819464034,
+      "grad_norm": 1.3777767419815063,
+      "learning_rate": 4.335877016290326e-06,
+      "loss": 0.2449,
+      "step": 815
+    },
+    {
+      "epoch": 2.310296191819464,
+      "grad_norm": 1.0245784521102905,
+      "learning_rate": 4.173273967741184e-06,
+      "loss": 0.2688,
+      "step": 820
+    },
+    {
+      "epoch": 2.324400564174894,
+      "grad_norm": 1.0006110668182373,
+      "learning_rate": 4.013284439346143e-06,
+      "loss": 0.2621,
+      "step": 825
+    },
+    {
+      "epoch": 2.3385049365303243,
+      "grad_norm": 1.0841772556304932,
+      "learning_rate": 3.855947051816179e-06,
+      "loss": 0.2804,
+      "step": 830
+    },
+    {
+      "epoch": 2.3526093088857545,
+      "grad_norm": 1.082770586013794,
+      "learning_rate": 3.7012997856480797e-06,
+      "loss": 0.2383,
+      "step": 835
+    },
+    {
+      "epoch": 2.3667136812411846,
+      "grad_norm": 1.041503667831421,
+      "learning_rate": 3.5493799719561415e-06,
+      "loss": 0.2566,
+      "step": 840
+    },
+    {
+      "epoch": 2.380818053596615,
+      "grad_norm": 0.9786086082458496,
+      "learning_rate": 3.4002242834606023e-06,
+      "loss": 0.2847,
+      "step": 845
+    },
+    {
+      "epoch": 2.394922425952045,
+      "grad_norm": 0.9603484272956848,
+      "learning_rate": 3.2538687256350297e-06,
+      "loss": 0.2849,
+      "step": 850
+    },
+    {
+      "epoch": 2.409026798307475,
+      "grad_norm": 1.156825304031372,
+      "learning_rate": 3.1103486280147624e-06,
+      "loss": 0.2352,
+      "step": 855
+    },
+    {
+      "epoch": 2.4231311706629057,
+      "grad_norm": 1.084373116493225,
+      "learning_rate": 2.969698635668553e-06,
+      "loss": 0.2925,
+      "step": 860
+    },
+    {
+      "epoch": 2.4372355430183354,
+      "grad_norm": 1.0228191614151,
+      "learning_rate": 2.8319527008353863e-06,
+      "loss": 0.2744,
+      "step": 865
+    },
+    {
+      "epoch": 2.451339915373766,
+      "grad_norm": 1.214138150215149,
+      "learning_rate": 2.697144074728577e-06,
+      "loss": 0.2816,
+      "step": 870
+    },
+    {
+      "epoch": 2.465444287729196,
+      "grad_norm": 1.211748480796814,
+      "learning_rate": 2.5653052995090927e-06,
+      "loss": 0.2855,
+      "step": 875
+    },
+    {
+      "epoch": 2.4795486600846264,
+      "grad_norm": 1.0586134195327759,
+      "learning_rate": 2.4364682004300193e-06,
+      "loss": 0.2746,
+      "step": 880
+    },
+    {
+      "epoch": 2.4936530324400565,
+      "grad_norm": 1.110299825668335,
+      "learning_rate": 2.3106638781541174e-06,
+      "loss": 0.2726,
+      "step": 885
+    },
+    {
+      "epoch": 2.5077574047954867,
+      "grad_norm": 1.1370130777359009,
+      "learning_rate": 2.1879227012462443e-06,
+      "loss": 0.2605,
+      "step": 890
+    },
+    {
+      "epoch": 2.521861777150917,
+      "grad_norm": 1.0158460140228271,
+      "learning_rate": 2.068274298842537e-06,
+      "loss": 0.2736,
+      "step": 895
+    },
+    {
+      "epoch": 2.535966149506347,
+      "grad_norm": 1.277999997138977,
+      "learning_rate": 1.951747553498094e-06,
+      "loss": 0.244,
+      "step": 900
+    },
+    {
+      "epoch": 2.550070521861777,
+      "grad_norm": 1.0778658390045166,
+      "learning_rate": 1.838370594214845e-06,
+      "loss": 0.2749,
+      "step": 905
+    },
+    {
+      "epoch": 2.5641748942172073,
+      "grad_norm": 1.0081775188446045,
+      "learning_rate": 1.7281707896513476e-06,
+      "loss": 0.2322,
+      "step": 910
+    },
+    {
+      "epoch": 2.5782792665726375,
+      "grad_norm": 1.042402982711792,
+      "learning_rate": 1.6211747415161283e-06,
+      "loss": 0.2732,
+      "step": 915
+    },
+    {
+      "epoch": 2.5923836389280677,
+      "grad_norm": 1.2807204723358154,
+      "learning_rate": 1.5174082781461507e-06,
+      "loss": 0.2466,
+      "step": 920
+    },
+    {
+      "epoch": 2.606488011283498,
+      "grad_norm": 1.1214522123336792,
+      "learning_rate": 1.4168964482719916e-06,
+      "loss": 0.271,
+      "step": 925
+    },
+    {
+      "epoch": 2.620592383638928,
+      "grad_norm": 1.109918475151062,
+      "learning_rate": 1.3196635149711712e-06,
+      "loss": 0.2569,
+      "step": 930
+    },
+    {
+      "epoch": 2.634696755994358,
+      "grad_norm": 1.1553428173065186,
+      "learning_rate": 1.225732949811194e-06,
+      "loss": 0.2363,
+      "step": 935
+    },
+    {
+      "epoch": 2.6488011283497883,
+      "grad_norm": 0.9468647241592407,
+      "learning_rate": 1.1351274271835948e-06,
+      "loss": 0.2714,
+      "step": 940
+    },
+    {
+      "epoch": 2.6629055007052185,
+      "grad_norm": 1.0239369869232178,
+      "learning_rate": 1.0478688188304609e-06,
+      "loss": 0.2556,
+      "step": 945
+    },
+    {
+      "epoch": 2.6770098730606486,
+      "grad_norm": 1.1113874912261963,
+      "learning_rate": 9.63978188564706e-07,
+      "loss": 0.2677,
+      "step": 950
+    },
+    {
+      "epoch": 2.6911142454160792,
+      "grad_norm": 1.0857006311416626,
+      "learning_rate": 8.834757871853461e-07,
+      "loss": 0.2642,
+      "step": 955
+    },
+    {
+      "epoch": 2.705218617771509,
+      "grad_norm": 1.0541398525238037,
+      "learning_rate": 8.063810475890732e-07,
+      "loss": 0.2391,
+      "step": 960
+    },
+    {
+      "epoch": 2.7193229901269396,
+      "grad_norm": 1.0358614921569824,
+      "learning_rate": 7.327125800792306e-07,
+      "loss": 0.2609,
+      "step": 965
+    },
+    {
+      "epoch": 2.7334273624823693,
+      "grad_norm": 0.9600598812103271,
+      "learning_rate": 6.624881678733852e-07,
+      "loss": 0.2833,
+      "step": 970
+    },
+    {
+      "epoch": 2.7475317348378,
+      "grad_norm": 1.031545639038086,
+      "learning_rate": 5.957247628105428e-07,
+      "loss": 0.2295,
+      "step": 975
+    },
+    {
+      "epoch": 2.76163610719323,
+      "grad_norm": 1.0968694686889648,
+      "learning_rate": 5.324384812590416e-07,
+      "loss": 0.2376,
+      "step": 980
+    },
+    {
+      "epoch": 2.77574047954866,
+      "grad_norm": 1.0207226276397705,
+      "learning_rate": 4.726446002261542e-07,
+      "loss": 0.2597,
+      "step": 985
+    },
+    {
+      "epoch": 2.7898448519040904,
+      "grad_norm": 1.1568629741668701,
+      "learning_rate": 4.163575536702807e-07,
+      "loss": 0.2644,
+      "step": 990
+    },
+    {
+      "epoch": 2.8039492242595205,
+      "grad_norm": 0.9799429178237915,
+      "learning_rate": 3.6359092901666614e-07,
+      "loss": 0.2397,
+      "step": 995
+    },
+    {
+      "epoch": 2.8180535966149507,
+      "grad_norm": 1.115788459777832,
+      "learning_rate": 3.1435746387745543e-07,
+      "loss": 0.227,
+      "step": 1000
+    },
+    {
+      "epoch": 2.832157968970381,
+      "grad_norm": 1.0494121313095093,
+      "learning_rate": 2.686690429768918e-07,
+      "loss": 0.2387,
+      "step": 1005
+    },
+    {
+      "epoch": 2.846262341325811,
+      "grad_norm": 1.0012835264205933,
+      "learning_rate": 2.2653669528241271e-07,
+      "loss": 0.2613,
+      "step": 1010
+    },
+    {
+      "epoch": 2.860366713681241,
+      "grad_norm": 1.0095962285995483,
+      "learning_rate": 1.8797059134230188e-07,
+      "loss": 0.2219,
+      "step": 1015
+    },
+    {
+      "epoch": 2.8744710860366713,
+      "grad_norm": 1.003462553024292,
+      "learning_rate": 1.5298004083056093e-07,
+      "loss": 0.2846,
+      "step": 1020
+    },
+    {
+      "epoch": 2.8885754583921015,
+      "grad_norm": 1.011505365371704,
+      "learning_rate": 1.2157349029961406e-07,
+      "loss": 0.2406,
+      "step": 1025
+    },
+    {
+      "epoch": 2.9026798307475317,
+      "grad_norm": 1.0605393648147583,
+      "learning_rate": 9.375852114133221e-08,
+      "loss": 0.2513,
+      "step": 1030
+    },
+    {
+      "epoch": 2.916784203102962,
+      "grad_norm": 0.9922693967819214,
+      "learning_rate": 6.954184775693873e-08,
+      "loss": 0.2506,
+      "step": 1035
+    },
+    {
+      "epoch": 2.930888575458392,
+      "grad_norm": 0.989320695400238,
+      "learning_rate": 4.8929315936174224e-08,
+      "loss": 0.2663,
+      "step": 1040
+    },
+    {
+      "epoch": 2.944992947813822,
+      "grad_norm": 1.1450376510620117,
+      "learning_rate": 3.1925901446148707e-08,
+      "loss": 0.2505,
+      "step": 1045
+    },
+    {
+      "epoch": 2.9590973201692523,
+      "grad_norm": 1.0581278800964355,
+      "learning_rate": 1.8535708830225707e-08,
+      "loss": 0.23,
+      "step": 1050
+    },
+    {
+      "epoch": 2.9732016925246825,
+      "grad_norm": 1.020913004875183,
+      "learning_rate": 8.761970417198173e-09,
+      "loss": 0.266,
+      "step": 1055
+    },
+    {
+      "epoch": 2.987306064880113,
+      "grad_norm": 1.0527656078338623,
+      "learning_rate": 2.607045541015984e-09,
+      "loss": 0.2749,
+      "step": 1060
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.6017621755599976,
+      "learning_rate": 7.24199712615059e-11,
+      "loss": 0.2435,
+      "step": 1065
+    },
+    {
+      "epoch": 3.0,
+      "step": 1065,
+      "total_flos": 1.6555905027177185e+18,
+      "train_loss": 0.5416349868819188,
+      "train_runtime": 801.1996,
+      "train_samples_per_second": 42.461,
+      "train_steps_per_second": 1.329
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1065,
+  "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": 1.6555905027177185e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

11_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be88473475a1fdcdfd31991e5bcb956564d958753bed788d09eded1634d3d9a3
+size 8209