Add FFT checkpoint epoch 7

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 32768,
+  "pad_token_id": 770,
+  "transformers_version": "4.52.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f403a2972acc00000c81c5de49376c7b9af1e0290cba1f6c9ebd584d9c2076
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c9b54da444979c87aa04373bebd81446c680ab6c4d20dc684971ce80827ab7
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db01d7004473c62149e1254c5345fcdf6b3797d6d05780d3583b18e980ee760
+size 4546807800

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854a42033a96518b7593d3d60e66b5042d3174d43bba2f403536d54198b13e48
+size 15524012362

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be6a8d4b38dfc32a89bb75eb545a7dab39a5b77267c6d547a394dab6c632a408
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa4f1a4e798e028ccce997ccd582ba72d505aba0d00e2c21349da45ce511df6c
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba729b0aa4b6afe15f697e1e9c86af0eaacfdd648dad1144dc90e223b8741064
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b65cb5c4d19a6c0283c52c0d56e0fbe20fdfa45e8749550ae85aa7351decaa
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9472db522b9d13ccd3b8226b4a1da529ec38b055b88c703771ee4402de87915e
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[control_768]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

trainer_state.json

@@ -0,0 +1,1063 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04819277108433735,
+      "grad_norm": 21.375,
+      "learning_rate": 0.0,
+      "loss": 8.8219,
+      "step": 1
+    },
+    {
+      "epoch": 0.0963855421686747,
+      "grad_norm": 23.75,
+      "learning_rate": 5e-06,
+      "loss": 8.3499,
+      "step": 2
+    },
+    {
+      "epoch": 0.14457831325301204,
+      "grad_norm": 3.84375,
+      "learning_rate": 1e-05,
+      "loss": 8.5385,
+      "step": 3
+    },
+    {
+      "epoch": 0.1927710843373494,
+      "grad_norm": 3.921875,
+      "learning_rate": 1.5e-05,
+      "loss": 8.917,
+      "step": 4
+    },
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 18.125,
+      "learning_rate": 2e-05,
+      "loss": 8.6019,
+      "step": 5
+    },
+    {
+      "epoch": 0.2891566265060241,
+      "grad_norm": 42.25,
+      "learning_rate": 2.5e-05,
+      "loss": 8.1326,
+      "step": 6
+    },
+    {
+      "epoch": 0.3373493975903614,
+      "grad_norm": 23.375,
+      "learning_rate": 3e-05,
+      "loss": 8.5672,
+      "step": 7
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "grad_norm": 54.0,
+      "learning_rate": 3.5e-05,
+      "loss": 8.5995,
+      "step": 8
+    },
+    {
+      "epoch": 0.43373493975903615,
+      "grad_norm": 39.0,
+      "learning_rate": 4e-05,
+      "loss": 8.2674,
+      "step": 9
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 4.59375,
+      "learning_rate": 4.5e-05,
+      "loss": 8.478,
+      "step": 10
+    },
+    {
+      "epoch": 0.5301204819277109,
+      "grad_norm": 14.4375,
+      "learning_rate": 5e-05,
+      "loss": 8.5228,
+      "step": 11
+    },
+    {
+      "epoch": 0.5783132530120482,
+      "grad_norm": 20.5,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 8.626,
+      "step": 12
+    },
+    {
+      "epoch": 0.6265060240963856,
+      "grad_norm": 18.25,
+      "learning_rate": 6e-05,
+      "loss": 8.3092,
+      "step": 13
+    },
+    {
+      "epoch": 0.6746987951807228,
+      "grad_norm": 82.5,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 9.1598,
+      "step": 14
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 30.875,
+      "learning_rate": 7e-05,
+      "loss": 8.7052,
+      "step": 15
+    },
+    {
+      "epoch": 0.7710843373493976,
+      "grad_norm": 17.75,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 8.3344,
+      "step": 16
+    },
+    {
+      "epoch": 0.8192771084337349,
+      "grad_norm": 72.5,
+      "learning_rate": 8e-05,
+      "loss": 8.2508,
+      "step": 17
+    },
+    {
+      "epoch": 0.8674698795180723,
+      "grad_norm": 6.59375,
+      "learning_rate": 8.5e-05,
+      "loss": 8.1669,
+      "step": 18
+    },
+    {
+      "epoch": 0.9156626506024096,
+      "grad_norm": 16.125,
+      "learning_rate": 9e-05,
+      "loss": 8.5961,
+      "step": 19
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 19.125,
+      "learning_rate": 9.5e-05,
+      "loss": 8.1445,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.96875,
+      "learning_rate": 0.0001,
+      "loss": 8.7202,
+      "step": 21
+    },
+    {
+      "epoch": 1.0481927710843373,
+      "grad_norm": 11.9375,
+      "learning_rate": 9.999664033241933e-05,
+      "loss": 8.6632,
+      "step": 22
+    },
+    {
+      "epoch": 1.0963855421686748,
+      "grad_norm": 17.75,
+      "learning_rate": 9.998656178117193e-05,
+      "loss": 8.1439,
+      "step": 23
+    },
+    {
+      "epoch": 1.144578313253012,
+      "grad_norm": 40.75,
+      "learning_rate": 9.99697657006811e-05,
+      "loss": 8.3403,
+      "step": 24
+    },
+    {
+      "epoch": 1.1927710843373494,
+      "grad_norm": 6.3125,
+      "learning_rate": 9.994625434811671e-05,
+      "loss": 8.528,
+      "step": 25
+    },
+    {
+      "epoch": 1.2409638554216866,
+      "grad_norm": 35.5,
+      "learning_rate": 9.991603088309194e-05,
+      "loss": 8.3088,
+      "step": 26
+    },
+    {
+      "epoch": 1.2891566265060241,
+      "grad_norm": 16.875,
+      "learning_rate": 9.987909936723858e-05,
+      "loss": 8.4892,
+      "step": 27
+    },
+    {
+      "epoch": 1.3373493975903614,
+      "grad_norm": 6.25,
+      "learning_rate": 9.983546476366132e-05,
+      "loss": 8.7603,
+      "step": 28
+    },
+    {
+      "epoch": 1.3855421686746987,
+      "grad_norm": 7.75,
+      "learning_rate": 9.978513293627067e-05,
+      "loss": 7.9509,
+      "step": 29
+    },
+    {
+      "epoch": 1.4337349397590362,
+      "grad_norm": 11.3125,
+      "learning_rate": 9.9728110648995e-05,
+      "loss": 7.9856,
+      "step": 30
+    },
+    {
+      "epoch": 1.4819277108433735,
+      "grad_norm": 18.75,
+      "learning_rate": 9.96644055648715e-05,
+      "loss": 8.5658,
+      "step": 31
+    },
+    {
+      "epoch": 1.5301204819277108,
+      "grad_norm": 82.0,
+      "learning_rate": 9.959402624501636e-05,
+      "loss": 9.3586,
+      "step": 32
+    },
+    {
+      "epoch": 1.5783132530120483,
+      "grad_norm": 16.5,
+      "learning_rate": 9.95169821474744e-05,
+      "loss": 8.5405,
+      "step": 33
+    },
+    {
+      "epoch": 1.6265060240963856,
+      "grad_norm": 42.25,
+      "learning_rate": 9.943328362594788e-05,
+      "loss": 8.5593,
+      "step": 34
+    },
+    {
+      "epoch": 1.6746987951807228,
+      "grad_norm": 7.90625,
+      "learning_rate": 9.934294192840516e-05,
+      "loss": 8.1437,
+      "step": 35
+    },
+    {
+      "epoch": 1.7228915662650603,
+      "grad_norm": 10.125,
+      "learning_rate": 9.924596919556917e-05,
+      "loss": 8.3373,
+      "step": 36
+    },
+    {
+      "epoch": 1.7710843373493976,
+      "grad_norm": 3.34375,
+      "learning_rate": 9.914237845928573e-05,
+      "loss": 8.3734,
+      "step": 37
+    },
+    {
+      "epoch": 1.819277108433735,
+      "grad_norm": 3.96875,
+      "learning_rate": 9.903218364077243e-05,
+      "loss": 8.5859,
+      "step": 38
+    },
+    {
+      "epoch": 1.8674698795180724,
+      "grad_norm": 3.640625,
+      "learning_rate": 9.891539954874757e-05,
+      "loss": 8.4436,
+      "step": 39
+    },
+    {
+      "epoch": 1.9156626506024095,
+      "grad_norm": 43.75,
+      "learning_rate": 9.879204187744036e-05,
+      "loss": 8.4789,
+      "step": 40
+    },
+    {
+      "epoch": 1.963855421686747,
+      "grad_norm": 21.375,
+      "learning_rate": 9.866212720448148e-05,
+      "loss": 8.1899,
+      "step": 41
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.453125,
+      "learning_rate": 9.852567298867557e-05,
+      "loss": 8.7482,
+      "step": 42
+    },
+    {
+      "epoch": 2.0481927710843375,
+      "grad_norm": 5.96875,
+      "learning_rate": 9.838269756765484e-05,
+      "loss": 8.2939,
+      "step": 43
+    },
+    {
+      "epoch": 2.0963855421686746,
+      "grad_norm": 2.171875,
+      "learning_rate": 9.823322015541474e-05,
+      "loss": 8.429,
+      "step": 44
+    },
+    {
+      "epoch": 2.144578313253012,
+      "grad_norm": 2.8125,
+      "learning_rate": 9.807726083973192e-05,
+      "loss": 8.3389,
+      "step": 45
+    },
+    {
+      "epoch": 2.1927710843373496,
+      "grad_norm": 4.21875,
+      "learning_rate": 9.791484057946465e-05,
+      "loss": 7.7685,
+      "step": 46
+    },
+    {
+      "epoch": 2.2409638554216866,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.774598120173624e-05,
+      "loss": 8.1287,
+      "step": 47
+    },
+    {
+      "epoch": 2.289156626506024,
+      "grad_norm": 2.875,
+      "learning_rate": 9.75707053990018e-05,
+      "loss": 8.1238,
+      "step": 48
+    },
+    {
+      "epoch": 2.337349397590361,
+      "grad_norm": 1.3125,
+      "learning_rate": 9.738903672599857e-05,
+      "loss": 8.1123,
+      "step": 49
+    },
+    {
+      "epoch": 2.3855421686746987,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.720099959658062e-05,
+      "loss": 8.2993,
+      "step": 50
+    },
+    {
+      "epoch": 2.433734939759036,
+      "grad_norm": 2.78125,
+      "learning_rate": 9.700661928043786e-05,
+      "loss": 8.0,
+      "step": 51
+    },
+    {
+      "epoch": 2.4819277108433733,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.680592189970015e-05,
+      "loss": 8.3916,
+      "step": 52
+    },
+    {
+      "epoch": 2.5301204819277108,
+      "grad_norm": 41.25,
+      "learning_rate": 9.659893442542682e-05,
+      "loss": 8.0818,
+      "step": 53
+    },
+    {
+      "epoch": 2.5783132530120483,
+      "grad_norm": 4.0,
+      "learning_rate": 9.638568467398215e-05,
+      "loss": 8.276,
+      "step": 54
+    },
+    {
+      "epoch": 2.6265060240963853,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.61662013032972e-05,
+      "loss": 8.6371,
+      "step": 55
+    },
+    {
+      "epoch": 2.674698795180723,
+      "grad_norm": 2.265625,
+      "learning_rate": 9.594051380901859e-05,
+      "loss": 8.2015,
+      "step": 56
+    },
+    {
+      "epoch": 2.7228915662650603,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.570865252054461e-05,
+      "loss": 8.1813,
+      "step": 57
+    },
+    {
+      "epoch": 2.7710843373493974,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.547064859694943e-05,
+      "loss": 7.9804,
+      "step": 58
+    },
+    {
+      "epoch": 2.819277108433735,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.52265340227957e-05,
+      "loss": 8.4279,
+      "step": 59
+    },
+    {
+      "epoch": 2.8674698795180724,
+      "grad_norm": 1.34375,
+      "learning_rate": 9.497634160383626e-05,
+      "loss": 8.1364,
+      "step": 60
+    },
+    {
+      "epoch": 2.9156626506024095,
+      "grad_norm": 1.0390625,
+      "learning_rate": 9.472010496260545e-05,
+      "loss": 8.4042,
+      "step": 61
+    },
+    {
+      "epoch": 2.963855421686747,
+      "grad_norm": 1.0,
+      "learning_rate": 9.445785853390073e-05,
+      "loss": 8.5425,
+      "step": 62
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.95703125,
+      "learning_rate": 9.41896375601551e-05,
+      "loss": 8.3245,
+      "step": 63
+    },
+    {
+      "epoch": 3.0481927710843375,
+      "grad_norm": 1.203125,
+      "learning_rate": 9.391547808670096e-05,
+      "loss": 8.4545,
+      "step": 64
+    },
+    {
+      "epoch": 3.0963855421686746,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.36354169569261e-05,
+      "loss": 8.3195,
+      "step": 65
+    },
+    {
+      "epoch": 3.144578313253012,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.334949180732245e-05,
+      "loss": 8.0084,
+      "step": 66
+    },
+    {
+      "epoch": 3.1927710843373496,
+      "grad_norm": 1.1953125,
+      "learning_rate": 9.305774106242823e-05,
+      "loss": 8.1112,
+      "step": 67
+    },
+    {
+      "epoch": 3.2409638554216866,
+      "grad_norm": 1.2890625,
+      "learning_rate": 9.276020392966422e-05,
+      "loss": 7.919,
+      "step": 68
+    },
+    {
+      "epoch": 3.289156626506024,
+      "grad_norm": 1.84375,
+      "learning_rate": 9.245692039406479e-05,
+      "loss": 7.9248,
+      "step": 69
+    },
+    {
+      "epoch": 3.337349397590361,
+      "grad_norm": 0.8203125,
+      "learning_rate": 9.214793121290442e-05,
+      "loss": 8.2828,
+      "step": 70
+    },
+    {
+      "epoch": 3.3855421686746987,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.183327791022047e-05,
+      "loss": 8.3589,
+      "step": 71
+    },
+    {
+      "epoch": 3.433734939759036,
+      "grad_norm": 1.7421875,
+      "learning_rate": 9.151300277123301e-05,
+      "loss": 8.3782,
+      "step": 72
+    },
+    {
+      "epoch": 3.4819277108433733,
+      "grad_norm": 1.140625,
+      "learning_rate": 9.118714883666202e-05,
+      "loss": 7.9337,
+      "step": 73
+    },
+    {
+      "epoch": 3.5301204819277108,
+      "grad_norm": 1.2265625,
+      "learning_rate": 9.085575989694357e-05,
+      "loss": 7.9006,
+      "step": 74
+    },
+    {
+      "epoch": 3.5783132530120483,
+      "grad_norm": 1.1953125,
+      "learning_rate": 9.051888048634471e-05,
+      "loss": 7.9798,
+      "step": 75
+    },
+    {
+      "epoch": 3.6265060240963853,
+      "grad_norm": 1.84375,
+      "learning_rate": 9.017655587697885e-05,
+      "loss": 8.0473,
+      "step": 76
+    },
+    {
+      "epoch": 3.674698795180723,
+      "grad_norm": 2.265625,
+      "learning_rate": 8.982883207272163e-05,
+      "loss": 8.1255,
+      "step": 77
+    },
+    {
+      "epoch": 3.7228915662650603,
+      "grad_norm": 0.75,
+      "learning_rate": 8.947575580302878e-05,
+      "loss": 8.2798,
+      "step": 78
+    },
+    {
+      "epoch": 3.7710843373493974,
+      "grad_norm": 0.8984375,
+      "learning_rate": 8.911737451665617e-05,
+      "loss": 8.4047,
+      "step": 79
+    },
+    {
+      "epoch": 3.819277108433735,
+      "grad_norm": 3.171875,
+      "learning_rate": 8.875373637528335e-05,
+      "loss": 7.8474,
+      "step": 80
+    },
+    {
+      "epoch": 3.8674698795180724,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.838489024704131e-05,
+      "loss": 8.1407,
+      "step": 81
+    },
+    {
+      "epoch": 3.9156626506024095,
+      "grad_norm": 1.2578125,
+      "learning_rate": 8.801088569994522e-05,
+      "loss": 8.3991,
+      "step": 82
+    },
+    {
+      "epoch": 3.963855421686747,
+      "grad_norm": 2.015625,
+      "learning_rate": 8.763177299523317e-05,
+      "loss": 8.5433,
+      "step": 83
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.1875,
+      "learning_rate": 8.724760308061172e-05,
+      "loss": 7.9072,
+      "step": 84
+    },
+    {
+      "epoch": 4.048192771084337,
+      "grad_norm": 0.74609375,
+      "learning_rate": 8.685842758340912e-05,
+      "loss": 8.1488,
+      "step": 85
+    },
+    {
+      "epoch": 4.096385542168675,
+      "grad_norm": 0.86328125,
+      "learning_rate": 8.646429880363746e-05,
+      "loss": 7.912,
+      "step": 86
+    },
+    {
+      "epoch": 4.144578313253012,
+      "grad_norm": 1.1015625,
+      "learning_rate": 8.606526970696409e-05,
+      "loss": 7.9744,
+      "step": 87
+    },
+    {
+      "epoch": 4.192771084337349,
+      "grad_norm": 0.59765625,
+      "learning_rate": 8.566139391759378e-05,
+      "loss": 8.2197,
+      "step": 88
+    },
+    {
+      "epoch": 4.240963855421687,
+      "grad_norm": 0.76171875,
+      "learning_rate": 8.525272571106241e-05,
+      "loss": 8.1522,
+      "step": 89
+    },
+    {
+      "epoch": 4.289156626506024,
+      "grad_norm": 0.63671875,
+      "learning_rate": 8.483932000694295e-05,
+      "loss": 8.3984,
+      "step": 90
+    },
+    {
+      "epoch": 4.337349397590361,
+      "grad_norm": 0.83984375,
+      "learning_rate": 8.442123236146508e-05,
+      "loss": 7.976,
+      "step": 91
+    },
+    {
+      "epoch": 4.385542168674699,
+      "grad_norm": 0.8828125,
+      "learning_rate": 8.399851896004913e-05,
+      "loss": 8.0713,
+      "step": 92
+    },
+    {
+      "epoch": 4.433734939759036,
+      "grad_norm": 0.875,
+      "learning_rate": 8.357123660975553e-05,
+      "loss": 7.5872,
+      "step": 93
+    },
+    {
+      "epoch": 4.481927710843373,
+      "grad_norm": 0.69140625,
+      "learning_rate": 8.313944273165069e-05,
+      "loss": 7.8125,
+      "step": 94
+    },
+    {
+      "epoch": 4.530120481927711,
+      "grad_norm": 0.74609375,
+      "learning_rate": 8.270319535309035e-05,
+      "loss": 7.8665,
+      "step": 95
+    },
+    {
+      "epoch": 4.578313253012048,
+      "grad_norm": 0.7734375,
+      "learning_rate": 8.22625530999215e-05,
+      "loss": 8.192,
+      "step": 96
+    },
+    {
+      "epoch": 4.626506024096385,
+      "grad_norm": 0.90234375,
+      "learning_rate": 8.181757518860387e-05,
+      "loss": 7.6524,
+      "step": 97
+    },
+    {
+      "epoch": 4.674698795180722,
+      "grad_norm": 0.7890625,
+      "learning_rate": 8.136832141825196e-05,
+      "loss": 8.033,
+      "step": 98
+    },
+    {
+      "epoch": 4.72289156626506,
+      "grad_norm": 0.60546875,
+      "learning_rate": 8.091485216259886e-05,
+      "loss": 8.4809,
+      "step": 99
+    },
+    {
+      "epoch": 4.771084337349397,
+      "grad_norm": 0.57421875,
+      "learning_rate": 8.04572283618829e-05,
+      "loss": 8.5897,
+      "step": 100
+    },
+    {
+      "epoch": 4.8192771084337345,
+      "grad_norm": 0.8046875,
+      "learning_rate": 7.999551151465792e-05,
+      "loss": 8.1135,
+      "step": 101
+    },
+    {
+      "epoch": 4.867469879518072,
+      "grad_norm": 0.6328125,
+      "learning_rate": 7.952976366952888e-05,
+      "loss": 8.0242,
+      "step": 102
+    },
+    {
+      "epoch": 4.9156626506024095,
+      "grad_norm": 0.6640625,
+      "learning_rate": 7.906004741681321e-05,
+      "loss": 8.3623,
+      "step": 103
+    },
+    {
+      "epoch": 4.9638554216867465,
+      "grad_norm": 0.71484375,
+      "learning_rate": 7.858642588012957e-05,
+      "loss": 7.9387,
+      "step": 104
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.515625,
+      "learning_rate": 7.810896270791483e-05,
+      "loss": 8.7533,
+      "step": 105
+    },
+    {
+      "epoch": 5.048192771084337,
+      "grad_norm": 0.421875,
+      "learning_rate": 7.762772206487066e-05,
+      "loss": 8.3158,
+      "step": 106
+    },
+    {
+      "epoch": 5.096385542168675,
+      "grad_norm": 0.64453125,
+      "learning_rate": 7.714276862334051e-05,
+      "loss": 7.8833,
+      "step": 107
+    },
+    {
+      "epoch": 5.144578313253012,
+      "grad_norm": 0.490234375,
+      "learning_rate": 7.665416755461859e-05,
+      "loss": 8.3018,
+      "step": 108
+    },
+    {
+      "epoch": 5.192771084337349,
+      "grad_norm": 0.5546875,
+      "learning_rate": 7.616198452019175e-05,
+      "loss": 8.2687,
+      "step": 109
+    },
+    {
+      "epoch": 5.240963855421687,
+      "grad_norm": 0.8125,
+      "learning_rate": 7.566628566291536e-05,
+      "loss": 7.5486,
+      "step": 110
+    },
+    {
+      "epoch": 5.289156626506024,
+      "grad_norm": 0.451171875,
+      "learning_rate": 7.516713759812465e-05,
+      "loss": 8.6013,
+      "step": 111
+    },
+    {
+      "epoch": 5.337349397590361,
+      "grad_norm": 0.66015625,
+      "learning_rate": 7.466460740468245e-05,
+      "loss": 8.0842,
+      "step": 112
+    },
+    {
+      "epoch": 5.385542168674699,
+      "grad_norm": 0.486328125,
+      "learning_rate": 7.415876261596474e-05,
+      "loss": 8.1395,
+      "step": 113
+    },
+    {
+      "epoch": 5.433734939759036,
+      "grad_norm": 0.72265625,
+      "learning_rate": 7.364967121078502e-05,
+      "loss": 7.2225,
+      "step": 114
+    },
+    {
+      "epoch": 5.481927710843373,
+      "grad_norm": 0.58203125,
+      "learning_rate": 7.313740160425887e-05,
+      "loss": 8.2312,
+      "step": 115
+    },
+    {
+      "epoch": 5.530120481927711,
+      "grad_norm": 0.435546875,
+      "learning_rate": 7.262202263860988e-05,
+      "loss": 8.2891,
+      "step": 116
+    },
+    {
+      "epoch": 5.578313253012048,
+      "grad_norm": 0.6171875,
+      "learning_rate": 7.210360357391818e-05,
+      "loss": 7.8645,
+      "step": 117
+    },
+    {
+      "epoch": 5.626506024096385,
+      "grad_norm": 0.55078125,
+      "learning_rate": 7.158221407881272e-05,
+      "loss": 7.4403,
+      "step": 118
+    },
+    {
+      "epoch": 5.674698795180722,
+      "grad_norm": 0.33203125,
+      "learning_rate": 7.105792422110885e-05,
+      "loss": 8.3234,
+      "step": 119
+    },
+    {
+      "epoch": 5.72289156626506,
+      "grad_norm": 0.40625,
+      "learning_rate": 7.05308044583921e-05,
+      "loss": 8.3879,
+      "step": 120
+    },
+    {
+      "epoch": 5.771084337349397,
+      "grad_norm": 0.76171875,
+      "learning_rate": 7.000092562854959e-05,
+      "loss": 8.3408,
+      "step": 121
+    },
+    {
+      "epoch": 5.8192771084337345,
+      "grad_norm": 0.5703125,
+      "learning_rate": 6.946835894025037e-05,
+      "loss": 8.0107,
+      "step": 122
+    },
+    {
+      "epoch": 5.867469879518072,
+      "grad_norm": 0.375,
+      "learning_rate": 6.893317596337592e-05,
+      "loss": 8.1194,
+      "step": 123
+    },
+    {
+      "epoch": 5.9156626506024095,
+      "grad_norm": 0.4609375,
+      "learning_rate": 6.839544861940214e-05,
+      "loss": 8.2629,
+      "step": 124
+    },
+    {
+      "epoch": 5.9638554216867465,
+      "grad_norm": 1.1484375,
+      "learning_rate": 6.785524917173399e-05,
+      "loss": 8.056,
+      "step": 125
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5234375,
+      "learning_rate": 6.731265021599436e-05,
+      "loss": 7.8151,
+      "step": 126
+    },
+    {
+      "epoch": 6.048192771084337,
+      "grad_norm": 0.421875,
+      "learning_rate": 6.676772467026808e-05,
+      "loss": 7.6327,
+      "step": 127
+    },
+    {
+      "epoch": 6.096385542168675,
+      "grad_norm": 0.287109375,
+      "learning_rate": 6.622054576530274e-05,
+      "loss": 8.0663,
+      "step": 128
+    },
+    {
+      "epoch": 6.144578313253012,
+      "grad_norm": 0.318359375,
+      "learning_rate": 6.567118703466746e-05,
+      "loss": 8.2473,
+      "step": 129
+    },
+    {
+      "epoch": 6.192771084337349,
+      "grad_norm": 0.462890625,
+      "learning_rate": 6.511972230487091e-05,
+      "loss": 7.6241,
+      "step": 130
+    },
+    {
+      "epoch": 6.240963855421687,
+      "grad_norm": 0.4609375,
+      "learning_rate": 6.456622568544012e-05,
+      "loss": 8.3676,
+      "step": 131
+    },
+    {
+      "epoch": 6.289156626506024,
+      "grad_norm": 0.359375,
+      "learning_rate": 6.401077155896099e-05,
+      "loss": 8.3317,
+      "step": 132
+    },
+    {
+      "epoch": 6.337349397590361,
+      "grad_norm": 0.4921875,
+      "learning_rate": 6.345343457108237e-05,
+      "loss": 8.2049,
+      "step": 133
+    },
+    {
+      "epoch": 6.385542168674699,
+      "grad_norm": 0.42578125,
+      "learning_rate": 6.289428962048467e-05,
+      "loss": 7.9903,
+      "step": 134
+    },
+    {
+      "epoch": 6.433734939759036,
+      "grad_norm": 0.34375,
+      "learning_rate": 6.233341184881441e-05,
+      "loss": 7.7185,
+      "step": 135
+    },
+    {
+      "epoch": 6.481927710843373,
+      "grad_norm": 0.349609375,
+      "learning_rate": 6.177087663058626e-05,
+      "loss": 7.9223,
+      "step": 136
+    },
+    {
+      "epoch": 6.530120481927711,
+      "grad_norm": 0.30859375,
+      "learning_rate": 6.120675956305363e-05,
+      "loss": 8.0702,
+      "step": 137
+    },
+    {
+      "epoch": 6.578313253012048,
+      "grad_norm": 0.4140625,
+      "learning_rate": 6.0641136456049454e-05,
+      "loss": 8.0074,
+      "step": 138
+    },
+    {
+      "epoch": 6.626506024096385,
+      "grad_norm": 0.3203125,
+      "learning_rate": 6.0074083321798355e-05,
+      "loss": 8.2116,
+      "step": 139
+    },
+    {
+      "epoch": 6.674698795180722,
+      "grad_norm": 0.296875,
+      "learning_rate": 5.95056763647016e-05,
+      "loss": 8.1088,
+      "step": 140
+    },
+    {
+      "epoch": 6.72289156626506,
+      "grad_norm": 0.416015625,
+      "learning_rate": 5.893599197109625e-05,
+      "loss": 7.7871,
+      "step": 141
+    },
+    {
+      "epoch": 6.771084337349397,
+      "grad_norm": 0.36328125,
+      "learning_rate": 5.8365106698989834e-05,
+      "loss": 8.3745,
+      "step": 142
+    },
+    {
+      "epoch": 6.8192771084337345,
+      "grad_norm": 0.3203125,
+      "learning_rate": 5.7793097267772e-05,
+      "loss": 7.8425,
+      "step": 143
+    },
+    {
+      "epoch": 6.867469879518072,
+      "grad_norm": 0.431640625,
+      "learning_rate": 5.722004054790442e-05,
+      "loss": 7.8534,
+      "step": 144
+    },
+    {
+      "epoch": 6.9156626506024095,
+      "grad_norm": 0.29296875,
+      "learning_rate": 5.664601355059044e-05,
+      "loss": 8.1238,
+      "step": 145
+    },
+    {
+      "epoch": 6.9638554216867465,
+      "grad_norm": 0.349609375,
+      "learning_rate": 5.607109341742579e-05,
+      "loss": 8.0837,
+      "step": 146
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.236328125,
+      "learning_rate": 5.5495357410031804e-05,
+      "loss": 8.7606,
+      "step": 147
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 291,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 14,
+  "save_steps": 21,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.95180970127786e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce8ee4d67fc559d7e92a3cb1e44373dd4ad27a3751325f5ceef60220f1863ad6
+size 6584