Training in progress, step 100, checkpoint

last-checkpoint/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

last-checkpoint/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "ModernLLMForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_modern_llm.ModernLLMConfig",
+    "AutoModelForCausalLM": "modeling_modern_llm.ModernLLMForCausalLM"
+  },
+  "bos_token_id": 151643,
+  "dtype": "float32",
+  "eos_token_id": 151643,
+  "hidden_size": 768,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 2048,
+  "model_type": "modern_llm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "transformers_version": "5.16.1",
+  "use_cache": false,
+  "vocab_size": 151936
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430eb8774ac7076b8fb0f635c836cc19b9c14bc3c222ea191c7c7b8587d4205e
+size 1235573136

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a53b13d5829f3ef1241485e2378a31fd793aff3c86fc84c451d7433cf504d7e0
+size 2471218763

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4393a84a3109995aa1202073b039b12062e3189ed89aa0b94ef0510ba843009
+size 1383

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116b971bb63560610677655e38ba8be2afb415c6fd29c1d069804301bcde855e
+size 1465

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2b7649a086fbb9771cd78ec5b7ffa7069e16a82424a382950fedfa1e057861
+size 11421991

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.025,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0025,
+      "grad_norm": 70.88893127441406,
+      "learning_rate": 2.6999999999999996e-05,
+      "loss": 191.82691650390626,
+      "step": 10
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 34.866336822509766,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 181.0546630859375,
+      "step": 20
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 26.507795333862305,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 168.4577392578125,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 26.122739791870117,
+      "learning_rate": 0.000117,
+      "loss": 155.47222900390625,
+      "step": 40
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 16.647830963134766,
+      "learning_rate": 0.000147,
+      "loss": 140.944287109375,
+      "step": 50
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 13.81060791015625,
+      "learning_rate": 0.00017699999999999997,
+      "loss": 130.086962890625,
+      "step": 60
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 17.337005615234375,
+      "learning_rate": 0.00020699999999999996,
+      "loss": 125.63973388671874,
+      "step": 70
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 20.01132583618164,
+      "learning_rate": 0.000237,
+      "loss": 124.44827880859376,
+      "step": 80
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 22.17510986328125,
+      "learning_rate": 0.000267,
+      "loss": 123.71231689453126,
+      "step": 90
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 18.62161636352539,
+      "learning_rate": 0.00029699999999999996,
+      "loss": 121.8670166015625,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1656326519032320.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21db9453d7d8ac6bfa4936e13632c57e87862815455df5498192c2b63e078d30
+size 5201