Upload folder using huggingface_hub

127_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": [
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

127_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da021621c1521e4314b928fd3d52488adfb1b94118d6fad1634b98fcd28c1c2
+size 791751704

127_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
+}

127_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.1897279902803558e+18,
+    "train_loss": 0.5869470324432641,
+    "train_runtime": 552.4582,
+    "train_samples": 9114,
+    "train_samples_per_second": 49.492,
+    "train_steps_per_second": 1.548
+}

127_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 %}

127_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
+}

127_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
+  }
+}

127_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
+}

127_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.1897279902803558e+18,
+    "train_loss": 0.5869470324432641,
+    "train_runtime": 552.4582,
+    "train_samples": 9114,
+    "train_samples_per_second": 49.492,
+    "train_steps_per_second": 1.548
+}

127_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1240 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 855,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017543859649122806,
+      "grad_norm": 3.365447998046875,
+      "learning_rate": 2.7906976744186046e-06,
+      "loss": 1.6129,
+      "step": 5
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 1.868890404701233,
+      "learning_rate": 6.279069767441861e-06,
+      "loss": 1.5087,
+      "step": 10
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.6818334460258484,
+      "learning_rate": 9.767441860465117e-06,
+      "loss": 1.442,
+      "step": 15
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 0.43484628200531006,
+      "learning_rate": 1.3255813953488373e-05,
+      "loss": 1.3637,
+      "step": 20
+    },
+    {
+      "epoch": 0.08771929824561403,
+      "grad_norm": 0.4852694869041443,
+      "learning_rate": 1.674418604651163e-05,
+      "loss": 1.3151,
+      "step": 25
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.4677450656890869,
+      "learning_rate": 2.0232558139534883e-05,
+      "loss": 1.3606,
+      "step": 30
+    },
+    {
+      "epoch": 0.12280701754385964,
+      "grad_norm": 0.460638165473938,
+      "learning_rate": 2.3720930232558138e-05,
+      "loss": 1.3032,
+      "step": 35
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 0.42829564213752747,
+      "learning_rate": 2.7209302325581395e-05,
+      "loss": 1.285,
+      "step": 40
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.35748788714408875,
+      "learning_rate": 2.9999887733958794e-05,
+      "loss": 1.2234,
+      "step": 45
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 0.39029461145401,
+      "learning_rate": 2.999595859896506e-05,
+      "loss": 1.2758,
+      "step": 50
+    },
+    {
+      "epoch": 0.19298245614035087,
+      "grad_norm": 0.4223393201828003,
+      "learning_rate": 2.9986417842286488e-05,
+      "loss": 1.2534,
+      "step": 55
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.44884243607521057,
+      "learning_rate": 2.9971269034159467e-05,
+      "loss": 1.1759,
+      "step": 60
+    },
+    {
+      "epoch": 0.22807017543859648,
+      "grad_norm": 0.4099855422973633,
+      "learning_rate": 2.9950517843403344e-05,
+      "loss": 1.2252,
+      "step": 65
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 0.3838435709476471,
+      "learning_rate": 2.992417203529909e-05,
+      "loss": 1.1695,
+      "step": 70
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.44891804456710815,
+      "learning_rate": 2.9892241468683476e-05,
+      "loss": 1.1421,
+      "step": 75
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 0.422260046005249,
+      "learning_rate": 2.985473809225981e-05,
+      "loss": 1.1301,
+      "step": 80
+    },
+    {
+      "epoch": 0.2982456140350877,
+      "grad_norm": 0.41603121161460876,
+      "learning_rate": 2.9811675940126604e-05,
+      "loss": 1.1572,
+      "step": 85
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.4591178596019745,
+      "learning_rate": 2.9763071126525923e-05,
+      "loss": 1.125,
+      "step": 90
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.4639914631843567,
+      "learning_rate": 2.970894183981326e-05,
+      "loss": 1.1515,
+      "step": 95
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.4674972593784332,
+      "learning_rate": 2.96493083356513e-05,
+      "loss": 1.0519,
+      "step": 100
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.5197584629058838,
+      "learning_rate": 2.9584192929430085e-05,
+      "loss": 1.0952,
+      "step": 105
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 0.5098059773445129,
+      "learning_rate": 2.9513619987916373e-05,
+      "loss": 1.0325,
+      "step": 110
+    },
+    {
+      "epoch": 0.40350877192982454,
+      "grad_norm": 0.4859628677368164,
+      "learning_rate": 2.9437615920135396e-05,
+      "loss": 1.0331,
+      "step": 115
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.5587638020515442,
+      "learning_rate": 2.9356209167488348e-05,
+      "loss": 1.0318,
+      "step": 120
+    },
+    {
+      "epoch": 0.43859649122807015,
+      "grad_norm": 0.5366851091384888,
+      "learning_rate": 2.9269430193109384e-05,
+      "loss": 1.0039,
+      "step": 125
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 0.5800937414169312,
+      "learning_rate": 2.9177311470466015e-05,
+      "loss": 0.9605,
+      "step": 130
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.6031177043914795,
+      "learning_rate": 2.9079887471207258e-05,
+      "loss": 0.964,
+      "step": 135
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 0.6035255789756775,
+      "learning_rate": 2.8977194652264048e-05,
+      "loss": 0.9871,
+      "step": 140
+    },
+    {
+      "epoch": 0.5087719298245614,
+      "grad_norm": 0.590595006942749,
+      "learning_rate": 2.8869271442206712e-05,
+      "loss": 0.9933,
+      "step": 145
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.9582504034042358,
+      "learning_rate": 2.875615822686466e-05,
+      "loss": 0.9429,
+      "step": 150
+    },
+    {
+      "epoch": 0.543859649122807,
+      "grad_norm": 0.6506302356719971,
+      "learning_rate": 2.8637897334213652e-05,
+      "loss": 0.9168,
+      "step": 155
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.6173605918884277,
+      "learning_rate": 2.8514533018536286e-05,
+      "loss": 0.9048,
+      "step": 160
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.6918940544128418,
+      "learning_rate": 2.838611144386166e-05,
+      "loss": 0.9018,
+      "step": 165
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.667086660861969,
+      "learning_rate": 2.8252680666690346e-05,
+      "loss": 0.8708,
+      "step": 170
+    },
+    {
+      "epoch": 0.6140350877192983,
+      "grad_norm": 0.6990797519683838,
+      "learning_rate": 2.811429061801127e-05,
+      "loss": 0.8741,
+      "step": 175
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.7447320818901062,
+      "learning_rate": 2.7970993084617058e-05,
+      "loss": 0.9044,
+      "step": 180
+    },
+    {
+      "epoch": 0.6491228070175439,
+      "grad_norm": 0.7422279715538025,
+      "learning_rate": 2.7822841689724952e-05,
+      "loss": 0.8511,
+      "step": 185
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.6780945062637329,
+      "learning_rate": 2.766989187291054e-05,
+      "loss": 0.8392,
+      "step": 190
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.6948316097259521,
+      "learning_rate": 2.7512200869361756e-05,
+      "loss": 0.8755,
+      "step": 195
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.7149096727371216,
+      "learning_rate": 2.7349827688460974e-05,
+      "loss": 0.7988,
+      "step": 200
+    },
+    {
+      "epoch": 0.7192982456140351,
+      "grad_norm": 0.7090550065040588,
+      "learning_rate": 2.718283309170317e-05,
+      "loss": 0.8832,
+      "step": 205
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.7440242171287537,
+      "learning_rate": 2.7011279569958407e-05,
+      "loss": 0.8399,
+      "step": 210
+    },
+    {
+      "epoch": 0.7543859649122807,
+      "grad_norm": 0.8195023536682129,
+      "learning_rate": 2.683523132008722e-05,
+      "loss": 0.8471,
+      "step": 215
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.8671055436134338,
+      "learning_rate": 2.665475422091757e-05,
+      "loss": 0.8108,
+      "step": 220
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.836410403251648,
+      "learning_rate": 2.6469915808592383e-05,
+      "loss": 0.7772,
+      "step": 225
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.8316211700439453,
+      "learning_rate": 2.628078525129694e-05,
+      "loss": 0.7606,
+      "step": 230
+    },
+    {
+      "epoch": 0.8245614035087719,
+      "grad_norm": 0.8611682057380676,
+      "learning_rate": 2.6087433323375506e-05,
+      "loss": 0.743,
+      "step": 235
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.8950226902961731,
+      "learning_rate": 2.5889932378846963e-05,
+      "loss": 0.7825,
+      "step": 240
+    },
+    {
+      "epoch": 0.8596491228070176,
+      "grad_norm": 0.8796069025993347,
+      "learning_rate": 2.568835632432927e-05,
+      "loss": 0.7216,
+      "step": 245
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.8016330003738403,
+      "learning_rate": 2.548278059138295e-05,
+      "loss": 0.7322,
+      "step": 250
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.8585559725761414,
+      "learning_rate": 2.527328210828392e-05,
+      "loss": 0.742,
+      "step": 255
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.8872100710868835,
+      "learning_rate": 2.5059939271236278e-05,
+      "loss": 0.7192,
+      "step": 260
+    },
+    {
+      "epoch": 0.9298245614035088,
+      "grad_norm": 0.8344059586524963,
+      "learning_rate": 2.4842831915035687e-05,
+      "loss": 0.747,
+      "step": 265
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.9721794724464417,
+      "learning_rate": 2.4622041283194517e-05,
+      "loss": 0.6886,
+      "step": 270
+    },
+    {
+      "epoch": 0.9649122807017544,
+      "grad_norm": 0.8954874277114868,
+      "learning_rate": 2.43976499975398e-05,
+      "loss": 0.6654,
+      "step": 275
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 1.0185184478759766,
+      "learning_rate": 2.4169742027295388e-05,
+      "loss": 0.7066,
+      "step": 280
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9839498996734619,
+      "learning_rate": 2.3938402657659924e-05,
+      "loss": 0.741,
+      "step": 285
+    },
+    {
+      "epoch": 1.0175438596491229,
+      "grad_norm": 0.88508540391922,
+      "learning_rate": 2.370371845789236e-05,
+      "loss": 0.6332,
+      "step": 290
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.9362666606903076,
+      "learning_rate": 2.3465777248916968e-05,
+      "loss": 0.5887,
+      "step": 295
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.9209312796592712,
+      "learning_rate": 2.3224668070459962e-05,
+      "loss": 0.5653,
+      "step": 300
+    },
+    {
+      "epoch": 1.0701754385964912,
+      "grad_norm": 1.0955981016159058,
+      "learning_rate": 2.298048114773005e-05,
+      "loss": 0.5753,
+      "step": 305
+    },
+    {
+      "epoch": 1.087719298245614,
+      "grad_norm": 1.1079777479171753,
+      "learning_rate": 2.2733307857655327e-05,
+      "loss": 0.5182,
+      "step": 310
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 1.0295618772506714,
+      "learning_rate": 2.248324069468924e-05,
+      "loss": 0.5894,
+      "step": 315
+    },
+    {
+      "epoch": 1.1228070175438596,
+      "grad_norm": 1.3059191703796387,
+      "learning_rate": 2.223037323619833e-05,
+      "loss": 0.5553,
+      "step": 320
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 1.0479726791381836,
+      "learning_rate": 2.1974800107444732e-05,
+      "loss": 0.5567,
+      "step": 325
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 1.2339802980422974,
+      "learning_rate": 2.1716616946176567e-05,
+      "loss": 0.555,
+      "step": 330
+    },
+    {
+      "epoch": 1.1754385964912282,
+      "grad_norm": 1.0587470531463623,
+      "learning_rate": 2.145592036683945e-05,
+      "loss": 0.5761,
+      "step": 335
+    },
+    {
+      "epoch": 1.1929824561403508,
+      "grad_norm": 1.0006828308105469,
+      "learning_rate": 2.119280792442249e-05,
+      "loss": 0.6025,
+      "step": 340
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 1.086309552192688,
+      "learning_rate": 2.0927378077952332e-05,
+      "loss": 0.5174,
+      "step": 345
+    },
+    {
+      "epoch": 1.2280701754385965,
+      "grad_norm": 1.0446141958236694,
+      "learning_rate": 2.0659730153648944e-05,
+      "loss": 0.5403,
+      "step": 350
+    },
+    {
+      "epoch": 1.2456140350877192,
+      "grad_norm": 1.0424203872680664,
+      "learning_rate": 2.0389964307756822e-05,
+      "loss": 0.5241,
+      "step": 355
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 1.0257900953292847,
+      "learning_rate": 2.0118181489065634e-05,
+      "loss": 0.5101,
+      "step": 360
+    },
+    {
+      "epoch": 1.280701754385965,
+      "grad_norm": 1.0167241096496582,
+      "learning_rate": 1.9844483401134322e-05,
+      "loss": 0.4906,
+      "step": 365
+    },
+    {
+      "epoch": 1.2982456140350878,
+      "grad_norm": 1.0771173238754272,
+      "learning_rate": 1.956897246423264e-05,
+      "loss": 0.481,
+      "step": 370
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 1.1480051279067993,
+      "learning_rate": 1.9291751777014676e-05,
+      "loss": 0.5018,
+      "step": 375
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.043609619140625,
+      "learning_rate": 1.9012925077938318e-05,
+      "loss": 0.5258,
+      "step": 380
+    },
+    {
+      "epoch": 1.3508771929824561,
+      "grad_norm": 1.0634889602661133,
+      "learning_rate": 1.8732596706445458e-05,
+      "loss": 0.5249,
+      "step": 385
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 1.1021512746810913,
+      "learning_rate": 1.8450871563917237e-05,
+      "loss": 0.5076,
+      "step": 390
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 1.0524097681045532,
+      "learning_rate": 1.8167855074418966e-05,
+      "loss": 0.4968,
+      "step": 395
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 1.0436317920684814,
+      "learning_rate": 1.7883653145249553e-05,
+      "loss": 0.4831,
+      "step": 400
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 1.0748012065887451,
+      "learning_rate": 1.7598372127310022e-05,
+      "loss": 0.4788,
+      "step": 405
+    },
+    {
+      "epoch": 1.4385964912280702,
+      "grad_norm": 1.1476844549179077,
+      "learning_rate": 1.7312118775306027e-05,
+      "loss": 0.4494,
+      "step": 410
+    },
+    {
+      "epoch": 1.456140350877193,
+      "grad_norm": 1.047548532485962,
+      "learning_rate": 1.702500020779935e-05,
+      "loss": 0.4483,
+      "step": 415
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 1.1079176664352417,
+      "learning_rate": 1.6737123867123135e-05,
+      "loss": 0.4799,
+      "step": 420
+    },
+    {
+      "epoch": 1.4912280701754386,
+      "grad_norm": 1.2839916944503784,
+      "learning_rate": 1.6448597479176004e-05,
+      "loss": 0.472,
+      "step": 425
+    },
+    {
+      "epoch": 1.5087719298245614,
+      "grad_norm": 1.0889285802841187,
+      "learning_rate": 1.6159529013110084e-05,
+      "loss": 0.525,
+      "step": 430
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 1.0689163208007812,
+      "learning_rate": 1.5870026640927978e-05,
+      "loss": 0.4272,
+      "step": 435
+    },
+    {
+      "epoch": 1.543859649122807,
+      "grad_norm": 1.0665310621261597,
+      "learning_rate": 1.5580198697003834e-05,
+      "loss": 0.4488,
+      "step": 440
+    },
+    {
+      "epoch": 1.5614035087719298,
+      "grad_norm": 1.101494550704956,
+      "learning_rate": 1.529015363754365e-05,
+      "loss": 0.4777,
+      "step": 445
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 1.2285206317901611,
+      "learning_rate": 1.5e-05,
+      "loss": 0.4466,
+      "step": 450
+    },
+    {
+      "epoch": 1.5964912280701755,
+      "grad_norm": 1.1330711841583252,
+      "learning_rate": 1.4709846362456356e-05,
+      "loss": 0.4161,
+      "step": 455
+    },
+    {
+      "epoch": 1.6140350877192984,
+      "grad_norm": 1.1162335872650146,
+      "learning_rate": 1.4419801302996167e-05,
+      "loss": 0.4321,
+      "step": 460
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 1.1052846908569336,
+      "learning_rate": 1.412997335907203e-05,
+      "loss": 0.4674,
+      "step": 465
+    },
+    {
+      "epoch": 1.6491228070175439,
+      "grad_norm": 1.093386173248291,
+      "learning_rate": 1.384047098688992e-05,
+      "loss": 0.4096,
+      "step": 470
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.0575740337371826,
+      "learning_rate": 1.3551402520824e-05,
+      "loss": 0.4591,
+      "step": 475
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 1.2008405923843384,
+      "learning_rate": 1.3262876132876868e-05,
+      "loss": 0.3886,
+      "step": 480
+    },
+    {
+      "epoch": 1.7017543859649122,
+      "grad_norm": 1.197770118713379,
+      "learning_rate": 1.2974999792200648e-05,
+      "loss": 0.3813,
+      "step": 485
+    },
+    {
+      "epoch": 1.719298245614035,
+      "grad_norm": 2.6354033946990967,
+      "learning_rate": 1.2687881224693972e-05,
+      "loss": 0.4672,
+      "step": 490
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 1.1755203008651733,
+      "learning_rate": 1.2401627872689987e-05,
+      "loss": 0.4331,
+      "step": 495
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "grad_norm": 1.0608446598052979,
+      "learning_rate": 1.2116346854750448e-05,
+      "loss": 0.4433,
+      "step": 500
+    },
+    {
+      "epoch": 1.7719298245614035,
+      "grad_norm": 1.005544662475586,
+      "learning_rate": 1.1832144925581037e-05,
+      "loss": 0.4058,
+      "step": 505
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 1.2564553022384644,
+      "learning_rate": 1.1549128436082767e-05,
+      "loss": 0.4023,
+      "step": 510
+    },
+    {
+      "epoch": 1.807017543859649,
+      "grad_norm": 1.0956538915634155,
+      "learning_rate": 1.1267403293554541e-05,
+      "loss": 0.4192,
+      "step": 515
+    },
+    {
+      "epoch": 1.8245614035087718,
+      "grad_norm": 1.1021091938018799,
+      "learning_rate": 1.098707492206169e-05,
+      "loss": 0.4213,
+      "step": 520
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 1.2100882530212402,
+      "learning_rate": 1.0708248222985333e-05,
+      "loss": 0.4296,
+      "step": 525
+    },
+    {
+      "epoch": 1.8596491228070176,
+      "grad_norm": 1.0904150009155273,
+      "learning_rate": 1.0431027535767361e-05,
+      "loss": 0.4068,
+      "step": 530
+    },
+    {
+      "epoch": 1.8771929824561404,
+      "grad_norm": 1.0855680704116821,
+      "learning_rate": 1.0155516598865684e-05,
+      "loss": 0.4025,
+      "step": 535
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 1.1881295442581177,
+      "learning_rate": 9.881818510934363e-06,
+      "loss": 0.3646,
+      "step": 540
+    },
+    {
+      "epoch": 1.912280701754386,
+      "grad_norm": 1.1947931051254272,
+      "learning_rate": 9.610035692243182e-06,
+      "loss": 0.4222,
+      "step": 545
+    },
+    {
+      "epoch": 1.9298245614035088,
+      "grad_norm": 1.1359723806381226,
+      "learning_rate": 9.34026984635106e-06,
+      "loss": 0.393,
+      "step": 550
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 1.0944252014160156,
+      "learning_rate": 9.072621922047672e-06,
+      "loss": 0.3829,
+      "step": 555
+    },
+    {
+      "epoch": 1.9649122807017543,
+      "grad_norm": 1.1211400032043457,
+      "learning_rate": 8.807192075577517e-06,
+      "loss": 0.4394,
+      "step": 560
+    },
+    {
+      "epoch": 1.9824561403508771,
+      "grad_norm": 1.1907384395599365,
+      "learning_rate": 8.544079633160553e-06,
+      "loss": 0.4222,
+      "step": 565
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.2017731666564941,
+      "learning_rate": 8.283383053823432e-06,
+      "loss": 0.3786,
+      "step": 570
+    },
+    {
+      "epoch": 2.017543859649123,
+      "grad_norm": 1.0769821405410767,
+      "learning_rate": 8.025199892555272e-06,
+      "loss": 0.3052,
+      "step": 575
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 1.1510818004608154,
+      "learning_rate": 7.769626763801676e-06,
+      "loss": 0.2684,
+      "step": 580
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 1.3417595624923706,
+      "learning_rate": 7.51675930531076e-06,
+      "loss": 0.2912,
+      "step": 585
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 1.183869481086731,
+      "learning_rate": 7.266692142344673e-06,
+      "loss": 0.2946,
+      "step": 590
+    },
+    {
+      "epoch": 2.087719298245614,
+      "grad_norm": 1.1304445266723633,
+      "learning_rate": 7.019518852269953e-06,
+      "loss": 0.3293,
+      "step": 595
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 1.090720534324646,
+      "learning_rate": 6.7753319295400354e-06,
+      "loss": 0.3152,
+      "step": 600
+    },
+    {
+      "epoch": 2.1228070175438596,
+      "grad_norm": 1.1204766035079956,
+      "learning_rate": 6.534222751083036e-06,
+      "loss": 0.3356,
+      "step": 605
+    },
+    {
+      "epoch": 2.1403508771929824,
+      "grad_norm": 1.0715309381484985,
+      "learning_rate": 6.296281542107647e-06,
+      "loss": 0.3108,
+      "step": 610
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 1.095884919166565,
+      "learning_rate": 6.061597342340079e-06,
+      "loss": 0.3075,
+      "step": 615
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 1.1767293214797974,
+      "learning_rate": 5.830257972704612e-06,
+      "loss": 0.2848,
+      "step": 620
+    },
+    {
+      "epoch": 2.192982456140351,
+      "grad_norm": 1.4315632581710815,
+      "learning_rate": 5.602350002460202e-06,
+      "loss": 0.3052,
+      "step": 625
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 1.145760178565979,
+      "learning_rate": 5.377958716805489e-06,
+      "loss": 0.3101,
+      "step": 630
+    },
+    {
+      "epoch": 2.2280701754385963,
+      "grad_norm": 1.362125277519226,
+      "learning_rate": 5.157168084964318e-06,
+      "loss": 0.3097,
+      "step": 635
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 1.160271406173706,
+      "learning_rate": 4.940060728763723e-06,
+      "loss": 0.2957,
+      "step": 640
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 1.0470812320709229,
+      "learning_rate": 4.726717891716079e-06,
+      "loss": 0.3133,
+      "step": 645
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 1.1131538152694702,
+      "learning_rate": 4.517219408617054e-06,
+      "loss": 0.2811,
+      "step": 650
+    },
+    {
+      "epoch": 2.2982456140350878,
+      "grad_norm": 1.1050890684127808,
+      "learning_rate": 4.311643675670729e-06,
+      "loss": 0.2626,
+      "step": 655
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 1.1520367860794067,
+      "learning_rate": 4.110067621153041e-06,
+      "loss": 0.2475,
+      "step": 660
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 1.3137457370758057,
+      "learning_rate": 3.912566676624497e-06,
+      "loss": 0.2862,
+      "step": 665
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 1.2810534238815308,
+      "learning_rate": 3.719214748703062e-06,
+      "loss": 0.279,
+      "step": 670
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 1.1183151006698608,
+      "learning_rate": 3.5300841914076183e-06,
+      "loss": 0.2606,
+      "step": 675
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 1.3264744281768799,
+      "learning_rate": 3.3452457790824293e-06,
+      "loss": 0.3098,
+      "step": 680
+    },
+    {
+      "epoch": 2.4035087719298245,
+      "grad_norm": 1.2024227380752563,
+      "learning_rate": 3.1647686799127794e-06,
+      "loss": 0.2862,
+      "step": 685
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 1.097076416015625,
+      "learning_rate": 2.9887204300415953e-06,
+      "loss": 0.2632,
+      "step": 690
+    },
+    {
+      "epoch": 2.43859649122807,
+      "grad_norm": 1.1867847442626953,
+      "learning_rate": 2.8171669082968348e-06,
+      "loss": 0.3025,
+      "step": 695
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 1.0100340843200684,
+      "learning_rate": 2.650172311539027e-06,
+      "loss": 0.2776,
+      "step": 700
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 1.1126737594604492,
+      "learning_rate": 2.4877991306382437e-06,
+      "loss": 0.2951,
+      "step": 705
+    },
+    {
+      "epoch": 2.4912280701754383,
+      "grad_norm": 1.19154953956604,
+      "learning_rate": 2.330108127089462e-06,
+      "loss": 0.2873,
+      "step": 710
+    },
+    {
+      "epoch": 2.5087719298245617,
+      "grad_norm": 1.2137471437454224,
+      "learning_rate": 2.177158310275051e-06,
+      "loss": 0.2647,
+      "step": 715
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 1.1337919235229492,
+      "learning_rate": 2.0290069153829425e-06,
+      "loss": 0.3076,
+      "step": 720
+    },
+    {
+      "epoch": 2.543859649122807,
+      "grad_norm": 1.1480627059936523,
+      "learning_rate": 1.885709381988731e-06,
+      "loss": 0.2799,
+      "step": 725
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 1.0965641736984253,
+      "learning_rate": 1.7473193333096576e-06,
+      "loss": 0.2592,
+      "step": 730
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 1.1765202283859253,
+      "learning_rate": 1.613888556138345e-06,
+      "loss": 0.3001,
+      "step": 735
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 1.1111934185028076,
+      "learning_rate": 1.4854669814637145e-06,
+      "loss": 0.2968,
+      "step": 740
+    },
+    {
+      "epoch": 2.6140350877192984,
+      "grad_norm": 1.2152196168899536,
+      "learning_rate": 1.3621026657863505e-06,
+      "loss": 0.2699,
+      "step": 745
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 1.1141629219055176,
+      "learning_rate": 1.2438417731353424e-06,
+      "loss": 0.2952,
+      "step": 750
+    },
+    {
+      "epoch": 2.6491228070175437,
+      "grad_norm": 1.0660029649734497,
+      "learning_rate": 1.1307285577932902e-06,
+      "loss": 0.2997,
+      "step": 755
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.285502314567566,
+      "learning_rate": 1.0228053477359533e-06,
+      "loss": 0.2998,
+      "step": 760
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 1.203273057937622,
+      "learning_rate": 9.201125287927426e-07,
+      "loss": 0.2519,
+      "step": 765
+    },
+    {
+      "epoch": 2.7017543859649122,
+      "grad_norm": 1.213044285774231,
+      "learning_rate": 8.22688529533987e-07,
+      "loss": 0.2992,
+      "step": 770
+    },
+    {
+      "epoch": 2.719298245614035,
+      "grad_norm": 1.0845396518707275,
+      "learning_rate": 7.305698068906159e-07,
+      "loss": 0.3085,
+      "step": 775
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 1.106785774230957,
+      "learning_rate": 6.43790832511651e-07,
+      "loss": 0.2722,
+      "step": 780
+    },
+    {
+      "epoch": 2.754385964912281,
+      "grad_norm": 1.1623800992965698,
+      "learning_rate": 5.623840798646058e-07,
+      "loss": 0.2503,
+      "step": 785
+    },
+    {
+      "epoch": 2.7719298245614032,
+      "grad_norm": 1.183990240097046,
+      "learning_rate": 4.863800120836287e-07,
+      "loss": 0.2828,
+      "step": 790
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 1.0789499282836914,
+      "learning_rate": 4.158070705699174e-07,
+      "loss": 0.2668,
+      "step": 795
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 1.064156174659729,
+      "learning_rate": 3.5069166434870014e-07,
+      "loss": 0.287,
+      "step": 800
+    },
+    {
+      "epoch": 2.824561403508772,
+      "grad_norm": 1.2312177419662476,
+      "learning_rate": 2.9105816018674123e-07,
+      "loss": 0.271,
+      "step": 805
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 1.4167927503585815,
+      "learning_rate": 2.3692887347407654e-07,
+      "loss": 0.2556,
+      "step": 810
+    },
+    {
+      "epoch": 2.8596491228070176,
+      "grad_norm": 1.251451849937439,
+      "learning_rate": 1.8832405987339485e-07,
+      "loss": 0.2919,
+      "step": 815
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "grad_norm": 1.188820719718933,
+      "learning_rate": 1.4526190774019287e-07,
+      "loss": 0.291,
+      "step": 820
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 1.1191437244415283,
+      "learning_rate": 1.0775853131652635e-07,
+      "loss": 0.2899,
+      "step": 825
+    },
+    {
+      "epoch": 2.912280701754386,
+      "grad_norm": 1.1382777690887451,
+      "learning_rate": 7.582796470091358e-08,
+      "loss": 0.2592,
+      "step": 830
+    },
+    {
+      "epoch": 2.9298245614035086,
+      "grad_norm": 1.2150698900222778,
+      "learning_rate": 4.9482156596659666e-08,
+      "loss": 0.2893,
+      "step": 835
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 1.1517767906188965,
+      "learning_rate": 2.8730965840533253e-08,
+      "loss": 0.2685,
+      "step": 840
+    },
+    {
+      "epoch": 2.9649122807017543,
+      "grad_norm": 1.180580973625183,
+      "learning_rate": 1.3582157713512565e-08,
+      "loss": 0.2808,
+      "step": 845
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 1.0312762260437012,
+      "learning_rate": 4.041401034939884e-09,
+      "loss": 0.2769,
+      "step": 850
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.1315253973007202,
+      "learning_rate": 1.1226604120673222e-10,
+      "loss": 0.2639,
+      "step": 855
+    },
+    {
+      "epoch": 3.0,
+      "step": 855,
+      "total_flos": 1.1897279902803558e+18,
+      "train_loss": 0.5869470324432641,
+      "train_runtime": 552.4582,
+      "train_samples_per_second": 49.492,
+      "train_steps_per_second": 1.548
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 855,
+  "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": 1.1897279902803558e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

127_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029329279a7b00126f22d02d450cf3132103274b1dbc17fe9d84faa0ba8bfb79
+size 8273