Upload folder using huggingface_hub

117_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",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

117_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd158b9fed0ba4c643367107254ac02126cef1570bff11bc7b3411b44ef5d3d
+size 791751704

117_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
+}

117_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 5.7133254202464666e+17,
+    "train_loss": 0.41649710557628383,
+    "train_runtime": 270.6173,
+    "train_samples": 4694,
+    "train_samples_per_second": 52.037,
+    "train_steps_per_second": 1.63
+}

117_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 %}

117_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
+}

117_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
+  }
+}

117_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
+}

117_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 5.7133254202464666e+17,
+    "train_loss": 0.41649710557628383,
+    "train_runtime": 270.6173,
+    "train_samples": 4694,
+    "train_samples_per_second": 52.037,
+    "train_steps_per_second": 1.63
+}

117_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,659 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 441,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.034013605442176874,
+      "grad_norm": 2.4861462116241455,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 1.5768,
+      "step": 5
+    },
+    {
+      "epoch": 0.06802721088435375,
+      "grad_norm": 1.1151363849639893,
+      "learning_rate": 1.173913043478261e-05,
+      "loss": 1.5495,
+      "step": 10
+    },
+    {
+      "epoch": 0.10204081632653061,
+      "grad_norm": 0.5511616468429565,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 1.4187,
+      "step": 15
+    },
+    {
+      "epoch": 0.1360544217687075,
+      "grad_norm": 0.5980119109153748,
+      "learning_rate": 2.4782608695652175e-05,
+      "loss": 1.3535,
+      "step": 20
+    },
+    {
+      "epoch": 0.17006802721088435,
+      "grad_norm": 0.4693211317062378,
+      "learning_rate": 2.9999576350789992e-05,
+      "loss": 1.3424,
+      "step": 25
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 0.445502370595932,
+      "learning_rate": 2.9984751140989417e-05,
+      "loss": 1.2348,
+      "step": 30
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.48697221279144287,
+      "learning_rate": 2.994876739510005e-05,
+      "loss": 1.3112,
+      "step": 35
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 0.5540298223495483,
+      "learning_rate": 2.9891675922333125e-05,
+      "loss": 1.1442,
+      "step": 40
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 0.4409748613834381,
+      "learning_rate": 2.9813557336105277e-05,
+      "loss": 1.1398,
+      "step": 45
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 0.48334914445877075,
+      "learning_rate": 2.971452194021204e-05,
+      "loss": 1.0841,
+      "step": 50
+    },
+    {
+      "epoch": 0.3741496598639456,
+      "grad_norm": 0.5083784461021423,
+      "learning_rate": 2.9594709573078373e-05,
+      "loss": 1.0694,
+      "step": 55
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.5148270726203918,
+      "learning_rate": 2.9454289410306202e-05,
+      "loss": 1.0184,
+      "step": 60
+    },
+    {
+      "epoch": 0.4421768707482993,
+      "grad_norm": 0.6168522238731384,
+      "learning_rate": 2.929345972579768e-05,
+      "loss": 0.9445,
+      "step": 65
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.6462437510490417,
+      "learning_rate": 2.9112447611791563e-05,
+      "loss": 0.9608,
+      "step": 70
+    },
+    {
+      "epoch": 0.5102040816326531,
+      "grad_norm": 0.6894866824150085,
+      "learning_rate": 2.8911508658207956e-05,
+      "loss": 0.8544,
+      "step": 75
+    },
+    {
+      "epoch": 0.54421768707483,
+      "grad_norm": 0.6551101803779602,
+      "learning_rate": 2.8690926591754142e-05,
+      "loss": 0.8728,
+      "step": 80
+    },
+    {
+      "epoch": 0.5782312925170068,
+      "grad_norm": 0.7020857930183411,
+      "learning_rate": 2.8451012875301278e-05,
+      "loss": 0.8337,
+      "step": 85
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.9288758039474487,
+      "learning_rate": 2.8192106268097336e-05,
+      "loss": 0.8014,
+      "step": 90
+    },
+    {
+      "epoch": 0.6462585034013606,
+      "grad_norm": 0.7558920979499817,
+      "learning_rate": 2.7914572347437576e-05,
+      "loss": 0.8222,
+      "step": 95
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 0.8130670785903931,
+      "learning_rate": 2.7618802992467718e-05,
+      "loss": 0.6764,
+      "step": 100
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.7733405232429504,
+      "learning_rate": 2.7305215830848867e-05,
+      "loss": 0.6135,
+      "step": 105
+    },
+    {
+      "epoch": 0.7482993197278912,
+      "grad_norm": 0.8799344301223755,
+      "learning_rate": 2.697425364906534e-05,
+      "loss": 0.5916,
+      "step": 110
+    },
+    {
+      "epoch": 0.782312925170068,
+      "grad_norm": 0.8792915344238281,
+      "learning_rate": 2.6626383767208166e-05,
+      "loss": 0.5523,
+      "step": 115
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.814326822757721,
+      "learning_rate": 2.6262097379117015e-05,
+      "loss": 0.6536,
+      "step": 120
+    },
+    {
+      "epoch": 0.8503401360544217,
+      "grad_norm": 0.9226080775260925,
+      "learning_rate": 2.588190885881229e-05,
+      "loss": 0.5259,
+      "step": 125
+    },
+    {
+      "epoch": 0.8843537414965986,
+      "grad_norm": 1.012988805770874,
+      "learning_rate": 2.5486355034196686e-05,
+      "loss": 0.502,
+      "step": 130
+    },
+    {
+      "epoch": 0.9183673469387755,
+      "grad_norm": 1.0620313882827759,
+      "learning_rate": 2.5075994429051775e-05,
+      "loss": 0.536,
+      "step": 135
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.9030884504318237,
+      "learning_rate": 2.465140647439991e-05,
+      "loss": 0.4984,
+      "step": 140
+    },
+    {
+      "epoch": 0.9863945578231292,
+      "grad_norm": 1.0362858772277832,
+      "learning_rate": 2.4213190690345018e-05,
+      "loss": 0.4782,
+      "step": 145
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "grad_norm": 1.020705223083496,
+      "learning_rate": 2.3761965839547515e-05,
+      "loss": 0.4259,
+      "step": 150
+    },
+    {
+      "epoch": 1.054421768707483,
+      "grad_norm": 0.9619016647338867,
+      "learning_rate": 2.3298369053528632e-05,
+      "loss": 0.4066,
+      "step": 155
+    },
+    {
+      "epoch": 1.08843537414966,
+      "grad_norm": 1.1071436405181885,
+      "learning_rate": 2.282305493303785e-05,
+      "loss": 0.3951,
+      "step": 160
+    },
+    {
+      "epoch": 1.1224489795918366,
+      "grad_norm": 0.9433997273445129,
+      "learning_rate": 2.233669462375368e-05,
+      "loss": 0.3251,
+      "step": 165
+    },
+    {
+      "epoch": 1.1564625850340136,
+      "grad_norm": 1.081548810005188,
+      "learning_rate": 2.1839974868622956e-05,
+      "loss": 0.3713,
+      "step": 170
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 1.1556713581085205,
+      "learning_rate": 2.1333597038176704e-05,
+      "loss": 0.2889,
+      "step": 175
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.9247576594352722,
+      "learning_rate": 2.081827614019177e-05,
+      "loss": 0.2838,
+      "step": 180
+    },
+    {
+      "epoch": 1.2585034013605443,
+      "grad_norm": 1.2783454656600952,
+      "learning_rate": 2.0294739810096657e-05,
+      "loss": 0.3293,
+      "step": 185
+    },
+    {
+      "epoch": 1.2925170068027212,
+      "grad_norm": 1.349860668182373,
+      "learning_rate": 1.976372728354699e-05,
+      "loss": 0.2752,
+      "step": 190
+    },
+    {
+      "epoch": 1.3265306122448979,
+      "grad_norm": 0.9492438435554504,
+      "learning_rate": 1.9225988352621445e-05,
+      "loss": 0.2871,
+      "step": 195
+    },
+    {
+      "epoch": 1.3605442176870748,
+      "grad_norm": 1.338285207748413,
+      "learning_rate": 1.8682282307111988e-05,
+      "loss": 0.2476,
+      "step": 200
+    },
+    {
+      "epoch": 1.3945578231292517,
+      "grad_norm": 1.1724566221237183,
+      "learning_rate": 1.8133376862403233e-05,
+      "loss": 0.2347,
+      "step": 205
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.0771312713623047,
+      "learning_rate": 1.7580047075454877e-05,
+      "loss": 0.2262,
+      "step": 210
+    },
+    {
+      "epoch": 1.4625850340136055,
+      "grad_norm": 0.9262290596961975,
+      "learning_rate": 1.702307425041779e-05,
+      "loss": 0.2529,
+      "step": 215
+    },
+    {
+      "epoch": 1.4965986394557822,
+      "grad_norm": 0.9468739032745361,
+      "learning_rate": 1.646324483542902e-05,
+      "loss": 0.2147,
+      "step": 220
+    },
+    {
+      "epoch": 1.5306122448979593,
+      "grad_norm": 0.9337593913078308,
+      "learning_rate": 1.5901349312143503e-05,
+      "loss": 0.2122,
+      "step": 225
+    },
+    {
+      "epoch": 1.564625850340136,
+      "grad_norm": 0.9350939989089966,
+      "learning_rate": 1.533818107957038e-05,
+      "loss": 0.2006,
+      "step": 230
+    },
+    {
+      "epoch": 1.598639455782313,
+      "grad_norm": 0.9240731596946716,
+      "learning_rate": 1.4774535333790046e-05,
+      "loss": 0.2153,
+      "step": 235
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 1.0882505178451538,
+      "learning_rate": 1.4211207945133685e-05,
+      "loss": 0.2223,
+      "step": 240
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.9848899245262146,
+      "learning_rate": 1.3648994334410798e-05,
+      "loss": 0.1901,
+      "step": 245
+    },
+    {
+      "epoch": 1.7006802721088436,
+      "grad_norm": 1.1429297924041748,
+      "learning_rate": 1.3088688349771425e-05,
+      "loss": 0.2078,
+      "step": 250
+    },
+    {
+      "epoch": 1.7346938775510203,
+      "grad_norm": 1.1259537935256958,
+      "learning_rate": 1.2531081145788989e-05,
+      "loss": 0.1866,
+      "step": 255
+    },
+    {
+      "epoch": 1.7687074829931972,
+      "grad_norm": 1.0374486446380615,
+      "learning_rate": 1.1976960066346474e-05,
+      "loss": 0.1569,
+      "step": 260
+    },
+    {
+      "epoch": 1.8027210884353742,
+      "grad_norm": 1.014298915863037,
+      "learning_rate": 1.1427107532903298e-05,
+      "loss": 0.1469,
+      "step": 265
+    },
+    {
+      "epoch": 1.836734693877551,
+      "grad_norm": 0.9284662008285522,
+      "learning_rate": 1.0882299939712727e-05,
+      "loss": 0.1543,
+      "step": 270
+    },
+    {
+      "epoch": 1.870748299319728,
+      "grad_norm": 0.8737163543701172,
+      "learning_rate": 1.0343306557549662e-05,
+      "loss": 0.1562,
+      "step": 275
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 1.0222892761230469,
+      "learning_rate": 9.810888447496859e-06,
+      "loss": 0.1498,
+      "step": 280
+    },
+    {
+      "epoch": 1.9387755102040818,
+      "grad_norm": 0.9931624531745911,
+      "learning_rate": 9.285797386323237e-06,
+      "loss": 0.1317,
+      "step": 285
+    },
+    {
+      "epoch": 1.9727891156462585,
+      "grad_norm": 0.841507077217102,
+      "learning_rate": 8.768774804971705e-06,
+      "loss": 0.1641,
+      "step": 290
+    },
+    {
+      "epoch": 2.006802721088435,
+      "grad_norm": 0.7555279731750488,
+      "learning_rate": 8.260550741655337e-06,
+      "loss": 0.1476,
+      "step": 295
+    },
+    {
+      "epoch": 2.0408163265306123,
+      "grad_norm": 0.7100093364715576,
+      "learning_rate": 7.76184281104011e-06,
+      "loss": 0.098,
+      "step": 300
+    },
+    {
+      "epoch": 2.074829931972789,
+      "grad_norm": 0.8721324801445007,
+      "learning_rate": 7.273355190969783e-06,
+      "loss": 0.1206,
+      "step": 305
+    },
+    {
+      "epoch": 2.108843537414966,
+      "grad_norm": 0.798827052116394,
+      "learning_rate": 6.795777628163599e-06,
+      "loss": 0.1193,
+      "step": 310
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.69526207447052,
+      "learning_rate": 6.329784464290817e-06,
+      "loss": 0.0965,
+      "step": 315
+    },
+    {
+      "epoch": 2.17687074829932,
+      "grad_norm": 0.9221840500831604,
+      "learning_rate": 5.8760336837972355e-06,
+      "loss": 0.1146,
+      "step": 320
+    },
+    {
+      "epoch": 2.2108843537414966,
+      "grad_norm": 0.7513834834098816,
+      "learning_rate": 5.435165984828193e-06,
+      "loss": 0.0947,
+      "step": 325
+    },
+    {
+      "epoch": 2.2448979591836733,
+      "grad_norm": 0.708294689655304,
+      "learning_rate": 5.0078038745599e-06,
+      "loss": 0.0919,
+      "step": 330
+    },
+    {
+      "epoch": 2.2789115646258504,
+      "grad_norm": 0.9145306348800659,
+      "learning_rate": 4.594550790216508e-06,
+      "loss": 0.0913,
+      "step": 335
+    },
+    {
+      "epoch": 2.312925170068027,
+      "grad_norm": 0.6197192668914795,
+      "learning_rate": 4.195990247014025e-06,
+      "loss": 0.1025,
+      "step": 340
+    },
+    {
+      "epoch": 2.3469387755102042,
+      "grad_norm": 0.9404375553131104,
+      "learning_rate": 3.8126850142342114e-06,
+      "loss": 0.0902,
+      "step": 345
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.6044611930847168,
+      "learning_rate": 3.445176320591806e-06,
+      "loss": 0.09,
+      "step": 350
+    },
+    {
+      "epoch": 2.4149659863945576,
+      "grad_norm": 0.6373472809791565,
+      "learning_rate": 3.0939830900171603e-06,
+      "loss": 0.0813,
+      "step": 355
+    },
+    {
+      "epoch": 2.4489795918367347,
+      "grad_norm": 0.8186767101287842,
+      "learning_rate": 2.7596012089333015e-06,
+      "loss": 0.0892,
+      "step": 360
+    },
+    {
+      "epoch": 2.4829931972789114,
+      "grad_norm": 0.6517190337181091,
+      "learning_rate": 2.442502826062072e-06,
+      "loss": 0.0869,
+      "step": 365
+    },
+    {
+      "epoch": 2.5170068027210886,
+      "grad_norm": 0.6655259132385254,
+      "learning_rate": 2.1431356857480076e-06,
+      "loss": 0.079,
+      "step": 370
+    },
+    {
+      "epoch": 2.5510204081632653,
+      "grad_norm": 0.57017582654953,
+      "learning_rate": 1.8619224957413106e-06,
+      "loss": 0.0866,
+      "step": 375
+    },
+    {
+      "epoch": 2.5850340136054424,
+      "grad_norm": 0.4864528775215149,
+      "learning_rate": 1.5992603303325997e-06,
+      "loss": 0.0785,
+      "step": 380
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 0.8693593740463257,
+      "learning_rate": 1.3555200696822235e-06,
+      "loss": 0.0798,
+      "step": 385
+    },
+    {
+      "epoch": 2.6530612244897958,
+      "grad_norm": 0.6717327833175659,
+      "learning_rate": 1.1310458761358057e-06,
+      "loss": 0.0795,
+      "step": 390
+    },
+    {
+      "epoch": 2.687074829931973,
+      "grad_norm": 0.5929320454597473,
+      "learning_rate": 9.261547082654614e-07,
+      "loss": 0.069,
+      "step": 395
+    },
+    {
+      "epoch": 2.7210884353741496,
+      "grad_norm": 0.7237470746040344,
+      "learning_rate": 7.411358733228679e-07,
+      "loss": 0.0874,
+      "step": 400
+    },
+    {
+      "epoch": 2.7551020408163263,
+      "grad_norm": 0.5867580771446228,
+      "learning_rate": 5.762506187361206e-07,
+      "loss": 0.078,
+      "step": 405
+    },
+    {
+      "epoch": 2.7891156462585034,
+      "grad_norm": 0.7382880449295044,
+      "learning_rate": 4.317317632271889e-07,
+      "loss": 0.0656,
+      "step": 410
+    },
+    {
+      "epoch": 2.8231292517006805,
+      "grad_norm": 0.6183791160583496,
+      "learning_rate": 3.077833680708325e-07,
+      "loss": 0.0884,
+      "step": 415
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.7212443351745605,
+      "learning_rate": 2.0458044895916516e-07,
+      "loss": 0.0896,
+      "step": 420
+    },
+    {
+      "epoch": 2.891156462585034,
+      "grad_norm": 0.7504419088363647,
+      "learning_rate": 1.2226872887870278e-07,
+      "loss": 0.0735,
+      "step": 425
+    },
+    {
+      "epoch": 2.925170068027211,
+      "grad_norm": 0.5811727046966553,
+      "learning_rate": 6.096443234885729e-08,
+      "loss": 0.0696,
+      "step": 430
+    },
+    {
+      "epoch": 2.9591836734693877,
+      "grad_norm": 0.7303270697593689,
+      "learning_rate": 2.0754121312389074e-08,
+      "loss": 0.0716,
+      "step": 435
+    },
+    {
+      "epoch": 2.9931972789115644,
+      "grad_norm": 0.5270622372627258,
+      "learning_rate": 1.6945729095507733e-09,
+      "loss": 0.0766,
+      "step": 440
+    },
+    {
+      "epoch": 3.0,
+      "step": 441,
+      "total_flos": 5.7133254202464666e+17,
+      "train_loss": 0.41649710557628383,
+      "train_runtime": 270.6173,
+      "train_samples_per_second": 52.037,
+      "train_steps_per_second": 1.63
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 441,
+  "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": 5.7133254202464666e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

117_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17554ae618847d0eda1062f3e799f8758c96d2b015d43c626db1a43c8d73db75
+size 8273