add checkpoints/sft1.5b_lr1e5_bs32

.gitattributes

@@ -119,3 +119,6 @@ checkpoints/codi-single-3b/checkpoint-3000/tokenizer.json filter=lfs diff=lfs me
 checkpoints/codi-single-3b/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/codi-single-3b/wandb/offline-run-20260624_140152-pm1zc3bt/run-pm1zc3bt.wandb filter=lfs diff=lfs merge=lfs -text
 checkpoints/codi-single-3b/wandb/offline-run-20260624_191509-pzchjc4v/run-pzchjc4v.wandb filter=lfs diff=lfs merge=lfs -text
+checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/run-8u6a9bbf.wandb filter=lfs diff=lfs merge=lfs -text
+checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/run-f7zbl5g6.wandb filter=lfs diff=lfs merge=lfs -text

checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|action_sep|>": 151670,
+  "<|arg_sep|>": 151671,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|call_sep|>": 151666,
+  "<|end_of_text|>": 151673,
+  "<|endoftext|>": 151643,
+  "<|exception_sep|>": 151669,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|frame_sep|>": 151672,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|latent_end|>": 151675,
+  "<|latent_start|>": 151674,
+  "<|line_sep|>": 151667,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|return_sep|>": 151668,
+  "<|trace_context_start|>": 151665,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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 %}

checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151676
+}

checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "eos_token_id": [
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.6"
+}

checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a60852ffe133303364862403563d33d286ad15a6aaa795590f35383ec6f9b1
+size 3086668424

checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a790d654474f5dfe225f889afd0210313eb1083f942671f2c4b8e95a1c922b
+size 11424004

checkpoints/sft1.5b_lr1e5_bs32/checkpoint-6936/tokenizer_config.json

@@ -0,0 +1,295 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|trace_context_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<|call_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<|line_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<|return_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "<|exception_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|action_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|arg_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<|frame_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<|latent_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|latent_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoints/sft1.5b_lr1e5_bs32/wandb/debug-internal.log

@@ -0,0 +1,15 @@
+{"time":"2026-06-19T14:15:27.495513616+02:00","level":"INFO","msg":"wandb-core"}
+{"time":"2026-06-19T14:15:27.495530857+02:00","level":"INFO","msg":"stream: starting","core version":"0.27.2"}
+{"time":"2026-06-19T14:15:27.616112226+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-06-19T14:15:27.616134112+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-06-19T14:15:27.616150216+02:00","level":"INFO","msg":"stream: created new stream","id":"f7zbl5g6"}
+{"time":"2026-06-19T14:15:27.616287718+02:00","level":"INFO","msg":"handler: started"}
+{"time":"2026-06-19T14:15:27.618163388+02:00","level":"INFO","msg":"stream: started"}
+{"time":"2026-06-19T14:15:27.618208304+02:00","level":"INFO","msg":"writer: started","stream_id":"f7zbl5g6"}
+{"time":"2026-06-19T14:15:27.618225281+02:00","level":"INFO","msg":"sender: started"}
+{"time":"2026-06-19T14:15:27.632535917+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-06-19T14:15:27.632547267+02:00","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}
+{"time":"2026-06-19T17:06:21.280675611+02:00","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-06-19T17:06:21.281207168+02:00","level":"INFO","msg":"handler: closed"}
+{"time":"2026-06-19T17:06:21.28217981+02:00","level":"INFO","msg":"sender: closed"}
+{"time":"2026-06-19T17:06:21.282191245+02:00","level":"INFO","msg":"stream: all finished"}

checkpoints/sft1.5b_lr1e5_bs32/wandb/debug.log

@@ -0,0 +1,24 @@
+2026-06-19 14:15:27,122 INFO    MainThread:599607 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
+2026-06-19 14:15:27,122 INFO    MainThread:599607 [wandb_setup.py:_flush():81] Configure stats pid to 599607
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_init.py:setup_run_log_directory():723] Logging user logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug.log
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug-internal.log
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_init.py:init():766] calling init triggers
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
+config: {'model': 'model_weights/qwen2.5-coder-1.5b', 'output_dir': 'model_weights/sft-coder-1.5b', 'n_samples': -1, 'max_seq_len': 3072, 'max_frames': -1, 'epochs': 4.0, 'lr': 2e-05, 'batch_size': 1, 'grad_accum': 8, 'max_steps': -1, 'sources': ['mbpp', 'humaneval', 'pyx'], 'cache_dir': 'data/cache/sft_train', '_wandb': {}}
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_init.py:init():814] starting backend
+2026-06-19 14:15:27,485 INFO    MainThread:599607 [wandb_init.py:init():829] sending inform_init request
+2026-06-19 14:15:27,618 INFO    MainThread:599607 [wandb_init.py:init():834] backend started and connected
+2026-06-19 14:15:27,620 INFO    MainThread:599607 [wandb_init.py:init():904] updated telemetry
+2026-06-19 14:15:27,630 INFO    MainThread:599607 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
+2026-06-19 14:15:27,633 INFO    MainThread:599607 [wandb_init.py:init():972] starting run threads in backend
+2026-06-19 14:15:27,924 INFO    MainThread:599607 [wandb_run.py:_console_start():2523] atexit reg
+2026-06-19 14:15:27,924 INFO    MainThread:599607 [wandb_run.py:_redirect():2373] redirect: wrap_raw
+2026-06-19 14:15:27,924 INFO    MainThread:599607 [wandb_run.py:_redirect():2442] Wrapping output streams.
+2026-06-19 14:15:27,924 INFO    MainThread:599607 [wandb_run.py:_redirect():2465] Redirects installed.
+2026-06-19 14:15:27,928 INFO    MainThread:599607 [wandb_init.py:init():1010] run started, returning control to user process
+2026-06-19 14:15:33,043 INFO    MainThread:599607 [wandb_run.py:_config_callback():1346] config_cb None None {'vocab_size': 151676, 'max_position_embeddings': 32768, 'hidden_size': 1536, 'intermediate_size': 8960, 'num_hidden_layers': 28, 'num_attention_heads': 12, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 28, 'num_key_value_heads': 2, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'rope_theta': 1000000.0, 'rope_scaling': None, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'dtype': 'bfloat16', 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'architectures': ['Qwen2ForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 151643, 'eos_token_id': 151643, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '_name_or_path': 'model_weights/qwen2.5-coder-1.5b', 'transformers_version': '4.57.6', 'model_type': 'qwen2', 'tf_legacy_loss': False, 'use_bfloat16': False, 'output_attentions': False, 'output_dir': 'model_weights/sft-coder-1.5b', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 8, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 4.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': 'model_weights/sft-coder-1.5b/runs/Jun19_14-15-27_alvis4-37', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': {'use_reentrant': False}, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
+2026-06-19 14:15:33,047 INFO    MainThread:599607 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 1543314944 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x145bcdaf6ad0>>
+2026-06-19 14:15:33,047 INFO    MainThread:599607 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 1543314944 None
+2026-06-19 17:06:21,276 INFO    wandb-AsyncioManager-main:599607 [service_client.py:_forward_responses():122] Reached EOF.
+2026-06-19 17:06:21,276 INFO    wandb-AsyncioManager-main:599607 [mailbox.py:close():154] Closing mailbox, abandoning 0 handles.

checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/files/requirements.txt

@@ -0,0 +1,222 @@
+wheel==0.47.0
+triton==3.3.1
+ptyprocess==0.7.0
+pyzmq==27.1.0
+nvidia-cublas-cu12==12.6.4.1
+python-dateutil==2.9.0.post0
+rfc3339-validator==0.1.4
+pluggy==1.6.0
+grpclib==0.4.9
+attrs==26.1.0
+urllib3==2.7.0
+cffi==2.0.0
+openai==1.86.0
+async-lru==2.3.0
+cfgv==3.5.0
+httpcore==1.0.9
+bitsandbytes==0.49.2
+iniconfig==2.3.0
+nvidia-cuda-runtime-cu12==12.6.77
+jupyterlab_server==2.28.0
+latex2sympy2_extended==1.11.0
+jupyter-events==0.12.1
+docker==7.1.0
+ipywidgets==8.1.8
+blinker==1.9.0
+cbor2==6.1.2
+nvidia-cufft-cu12==11.3.0.4
+nvidia-cusolver-cu12==11.7.1.2
+multiprocess==0.70.16
+anyio==4.14.0
+itsdangerous==2.2.0
+widgetsnbextension==4.0.15
+watchfiles==1.2.0
+swebench==4.1.0
+blobfile==3.2.0
+jupyter==1.1.1
+certifi==2026.6.17
+argon2-cffi==25.1.0
+argon2-cffi-bindings==25.1.0
+overrides==7.7.0
+propcache==0.5.2
+ipython==8.33.0
+nbconvert==7.17.1
+rich==15.0.0
+asttokens==3.0.1
+tokenizers==0.22.2
+synchronicity==0.12.4
+tqdm==4.68.3
+nvidia-nvjitlink-cu12==12.6.85
+nvidia-nvtx-cu12==12.6.77
+jsonschema-specifications==2025.9.1
+jupyterlab==4.5.8
+pure_eval==0.2.3
+uri-template==1.3.0
+sentry-sdk==2.63.0
+pycryptodomex==3.23.0
+yarl==1.24.2
+h2==4.3.0
+h11==0.16.0
+requests==2.34.2
+Jinja2==3.1.6
+xformers==0.0.31.post1
+rfc3987-syntax==1.1.0
+antlr4-python3-runtime==4.11.0
+nvidia-cusparselt-cu12==0.6.3
+safetensors==0.8.0
+notebook_shim==0.2.4
+Pygments==2.20.0
+python-json-logger==4.1.0
+isoduration==20.11.0
+smmap==5.0.3
+click==8.3.3
+transformers==4.57.6
+aiohappyeyeballs==2.6.2
+regex==2026.5.9
+jsonpointer==3.1.1
+fqdn==1.5.1
+jupyter-lsp==2.3.1
+rfc3986-validator==0.1.1
+prometheus_client==0.25.0
+mistune==3.2.1
+sentencepiece==0.2.1
+types-toml==0.10.8.20260518
+wcwidth==0.8.1
+identify==2.6.19
+protobuf==6.33.6
+datasets==3.6.0
+accelerate==1.14.0
+networkx==3.6.1
+pydantic==2.13.4
+multidict==6.7.1
+chardet==7.4.3
+pytest==9.1.0
+babel==2.18.0
+pip==26.1.2
+dill==0.3.8
+referencing==0.37.0
+pre_commit==4.6.0
+numpy==2.4.6
+math-verify==0.9.0
+traitlets==5.15.1
+nvidia-curand-cu12==10.3.7.77
+websocket-client==1.9.0
+hf-xet==1.5.1
+unidiff==0.7.5
+nest-asyncio2==1.7.2
+typing_extensions==4.15.0
+platformdirs==4.10.0
+torch==2.7.1
+tblib==3.2.2
+sqlfluff==4.2.2
+modal==1.5.0
+ipykernel==7.3.0
+msgspec==0.21.1
+virtualenv==21.5.1
+json5==0.14.0
+pathlib_abc==0.5.2
+aiosignal==1.4.0
+moodist==0.5.1
+rpds-py==2026.5.1
+webencodings==0.5.1
+sniffio==1.3.1
+annotated-types==0.7.0
+python-discovery==1.4.2
+scipy==1.17.1
+GitPython==3.1.50
+defusedxml==0.7.1
+nvidia-cufile-cu12==1.11.1.6
+nvidia-nccl-cu12==2.26.2
+sympy==1.14.0
+tinycss2==1.5.1
+soupsieve==2.8.4
+ninja==1.13.0
+python-dotenv==1.2.2
+ghapi==1.0.13
+jupyter_server_terminals==0.5.4
+markdown-it-py==4.2.0
+nbclient==0.11.0
+mpmath==1.3.0
+frozenlist==1.8.0
+Werkzeug==3.1.8
+executing==2.2.1
+gitdb==4.0.12
+setuptools==82.0.1
+Flask==3.1.1
+MarkupSafe==3.0.3
+notebook==7.5.7
+jupyter_core==5.9.1
+jedi==0.20.0
+mdurl==0.1.2
+lark==1.3.1
+bleach==6.4.0
+hpack==4.1.0
+google-re2==1.1.20240702
+beautifulsoup4==4.15.0
+jsonschema==4.26.0
+psutil==7.2.2
+nvidia-cuda-nvrtc-cu12==12.6.77
+narwhals==2.22.1
+lxml==6.1.1
+fastjsonschema==2.21.2
+tornado==6.5.7
+nodeenv==1.10.0
+typing-inspection==0.4.2
+httpx==0.28.1
+distro==1.9.0
+colorama==0.4.6
+jupyter-console==6.6.3
+jupyterlab_widgets==3.0.16
+PyYAML==6.0.3
+fsspec==2025.3.0
+hyperframe==6.1.0
+nvidia-cuda-cupti-cu12==12.6.80
+charset-normalizer==3.4.7
+wandb==0.27.2
+nbformat==5.10.4
+nvidia-cudnn-cu12==9.5.1.17
+peft==0.19.1
+pathspec==1.1.1
+matplotlib-inline==0.2.2
+huggingface_hub==0.36.2
+pyarrow==24.0.0
+nvidia-cusparse-cu12==12.5.4.2
+cwm==0.0.1
+prompt_toolkit==3.0.52
+omegaconf==2.4.0.dev4
+tiktoken==0.13.0
+comm==0.2.3
+threadpoolctl==3.6.0
+pydantic_core==2.46.4
+tenacity==9.1.4
+parso==0.8.7
+pandas==3.0.3
+webcolors==25.10.0
+idna==3.18
+terminado==0.18.1
+pandocfilters==1.5.1
+aiohttp==3.14.1
+arrow==1.4.0
+packaging==26.2
+tzdata==2026.2
+distlib==0.4.3
+Send2Trash==2.1.0
+jupyterlab_pygments==0.3.0
+decorator==5.3.1
+jupyter_server==2.20.0
+scikit-learn==1.9.0
+six==1.17.0
+diff_cover==10.3.0
+pycparser==3.0
+types-certifi==2021.10.8.3
+toml==0.10.2
+stack-data==0.6.3
+fastcore==1.13.5
+filelock==3.29.4
+xxhash==3.7.0
+pexpect==4.9.0
+jupyter_client==8.9.1
+jiter==0.15.0
+debugpy==1.8.21
+universal_pathlib==0.3.10
+joblib==1.5.3

checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug-core.log

@@ -0,0 +1,6 @@
+{"time":"2026-06-19T13:52:53.756446026+02:00","level":"INFO","msg":"main: starting server","port-filename":"/local/tmp.6767576/tmpq69h57wa/port-5604.txt","pid":5604,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-06-19T13:52:53.756834913+02:00","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/local/tmp.6767576/wandb-5604-5808-4086320459/socket","Net":"unix"}}
+{"time":"2026-06-19T13:52:53.756910259+02:00","level":"INFO","msg":"server: will exit if parent process dies","ppid":5604}
+{"time":"2026-06-19T13:52:53.937561818+02:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-06-19T13:52:53.951667135+02:00","level":"INFO","msg":"handleInformInit: received","streamId":"8u6a9bbf","id":"1(@)"}
+{"time":"2026-06-19T13:52:54.084559321+02:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"8u6a9bbf","id":"1(@)"}

checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug-internal.log

@@ -0,0 +1,11 @@
+{"time":"2026-06-19T13:52:53.954447401+02:00","level":"INFO","msg":"wandb-core"}
+{"time":"2026-06-19T13:52:53.954460021+02:00","level":"INFO","msg":"stream: starting","core version":"0.27.2"}
+{"time":"2026-06-19T13:52:54.076642955+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-06-19T13:52:54.076659633+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-06-19T13:52:54.07667716+02:00","level":"INFO","msg":"stream: created new stream","id":"8u6a9bbf"}
+{"time":"2026-06-19T13:52:54.0767048+02:00","level":"INFO","msg":"handler: started"}
+{"time":"2026-06-19T13:52:54.084549674+02:00","level":"INFO","msg":"stream: started"}
+{"time":"2026-06-19T13:52:54.084679246+02:00","level":"INFO","msg":"writer: started","stream_id":"8u6a9bbf"}
+{"time":"2026-06-19T13:52:54.084703599+02:00","level":"INFO","msg":"sender: started"}
+{"time":"2026-06-19T13:52:54.093460106+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-06-19T13:52:54.09346915+02:00","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}

checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug.log

@@ -0,0 +1,22 @@
+2026-06-19 13:52:53,411 INFO    MainThread:5604 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
+2026-06-19 13:52:53,411 INFO    MainThread:5604 [wandb_setup.py:_flush():81] Configure stats pid to 5604
+2026-06-19 13:52:53,411 INFO    MainThread:5604 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-06-19 13:52:53,411 INFO    MainThread:5604 [wandb_init.py:setup_run_log_directory():723] Logging user logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug.log
+2026-06-19 13:52:53,411 INFO    MainThread:5604 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_135253-8u6a9bbf/logs/debug-internal.log
+2026-06-19 13:52:53,411 INFO    MainThread:5604 [wandb_init.py:init():766] calling init triggers
+2026-06-19 13:52:53,411 INFO    MainThread:5604 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
+config: {'model': 'model_weights/qwen2.5-coder-1.5b', 'output_dir': 'model_weights/sft-coder-1.5b', 'n_samples': -1, 'max_seq_len': 3072, 'max_frames': -1, 'epochs': 4.0, 'lr': 2e-05, 'batch_size': 2, 'grad_accum': 4, 'max_steps': -1, 'sources': ['mbpp', 'humaneval', 'pyx'], 'cache_dir': 'data/cache/sft_train', '_wandb': {}}
+2026-06-19 13:52:53,411 INFO    MainThread:5604 [wandb_init.py:init():814] starting backend
+2026-06-19 13:52:53,937 INFO    MainThread:5604 [wandb_init.py:init():829] sending inform_init request
+2026-06-19 13:52:54,085 INFO    MainThread:5604 [wandb_init.py:init():834] backend started and connected
+2026-06-19 13:52:54,086 INFO    MainThread:5604 [wandb_init.py:init():904] updated telemetry
+2026-06-19 13:52:54,092 INFO    MainThread:5604 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
+2026-06-19 13:52:54,094 INFO    MainThread:5604 [wandb_init.py:init():972] starting run threads in backend
+2026-06-19 13:52:54,689 INFO    MainThread:5604 [wandb_run.py:_console_start():2523] atexit reg
+2026-06-19 13:52:54,690 INFO    MainThread:5604 [wandb_run.py:_redirect():2373] redirect: wrap_raw
+2026-06-19 13:52:54,690 INFO    MainThread:5604 [wandb_run.py:_redirect():2442] Wrapping output streams.
+2026-06-19 13:52:54,690 INFO    MainThread:5604 [wandb_run.py:_redirect():2465] Redirects installed.
+2026-06-19 13:52:54,697 INFO    MainThread:5604 [wandb_init.py:init():1010] run started, returning control to user process
+2026-06-19 13:53:00,144 INFO    MainThread:5604 [wandb_run.py:_config_callback():1346] config_cb None None {'vocab_size': 151676, 'max_position_embeddings': 32768, 'hidden_size': 1536, 'intermediate_size': 8960, 'num_hidden_layers': 28, 'num_attention_heads': 12, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 28, 'num_key_value_heads': 2, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'rope_theta': 1000000.0, 'rope_scaling': None, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'dtype': 'bfloat16', 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'architectures': ['Qwen2ForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 151643, 'pad_token_id': None, 'eos_token_id': 151643, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '_name_or_path': 'model_weights/qwen2.5-coder-1.5b', 'transformers_version': '4.57.6', 'model_type': 'qwen2', 'tf_legacy_loss': False, 'use_bfloat16': False, 'output_attentions': False, 'output_dir': 'model_weights/sft-coder-1.5b', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 4.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': 'model_weights/sft-coder-1.5b/runs/Jun19_13-52-54_alvis5-11', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': {'use_reentrant': False}, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
+2026-06-19 13:53:00,148 INFO    MainThread:5604 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 1543314944 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x149ca8701290>>
+2026-06-19 13:53:00,148 INFO    MainThread:5604 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 1543314944 None

checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_135253-8u6a9bbf/run-8u6a9bbf.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be7899520edde22ffd32cd4b72c17ce18b0c6943d96c82e20e96b86766b7099
+size 196608

checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/files/requirements.txt

@@ -0,0 +1,222 @@
+wheel==0.47.0
+triton==3.3.1
+ptyprocess==0.7.0
+pyzmq==27.1.0
+nvidia-cublas-cu12==12.6.4.1
+python-dateutil==2.9.0.post0
+rfc3339-validator==0.1.4
+pluggy==1.6.0
+grpclib==0.4.9
+attrs==26.1.0
+urllib3==2.7.0
+cffi==2.0.0
+openai==1.86.0
+async-lru==2.3.0
+cfgv==3.5.0
+httpcore==1.0.9
+bitsandbytes==0.49.2
+iniconfig==2.3.0
+nvidia-cuda-runtime-cu12==12.6.77
+jupyterlab_server==2.28.0
+latex2sympy2_extended==1.11.0
+jupyter-events==0.12.1
+docker==7.1.0
+ipywidgets==8.1.8
+blinker==1.9.0
+cbor2==6.1.2
+nvidia-cufft-cu12==11.3.0.4
+nvidia-cusolver-cu12==11.7.1.2
+multiprocess==0.70.16
+anyio==4.14.0
+itsdangerous==2.2.0
+widgetsnbextension==4.0.15
+watchfiles==1.2.0
+swebench==4.1.0
+blobfile==3.2.0
+jupyter==1.1.1
+certifi==2026.6.17
+argon2-cffi==25.1.0
+argon2-cffi-bindings==25.1.0
+overrides==7.7.0
+propcache==0.5.2
+ipython==8.33.0
+nbconvert==7.17.1
+rich==15.0.0
+asttokens==3.0.1
+tokenizers==0.22.2
+synchronicity==0.12.4
+tqdm==4.68.3
+nvidia-nvjitlink-cu12==12.6.85
+nvidia-nvtx-cu12==12.6.77
+jsonschema-specifications==2025.9.1
+jupyterlab==4.5.8
+pure_eval==0.2.3
+uri-template==1.3.0
+sentry-sdk==2.63.0
+pycryptodomex==3.23.0
+yarl==1.24.2
+h2==4.3.0
+h11==0.16.0
+requests==2.34.2
+Jinja2==3.1.6
+xformers==0.0.31.post1
+rfc3987-syntax==1.1.0
+antlr4-python3-runtime==4.11.0
+nvidia-cusparselt-cu12==0.6.3
+safetensors==0.8.0
+notebook_shim==0.2.4
+Pygments==2.20.0
+python-json-logger==4.1.0
+isoduration==20.11.0
+smmap==5.0.3
+click==8.3.3
+transformers==4.57.6
+aiohappyeyeballs==2.6.2
+regex==2026.5.9
+jsonpointer==3.1.1
+fqdn==1.5.1
+jupyter-lsp==2.3.1
+rfc3986-validator==0.1.1
+prometheus_client==0.25.0
+mistune==3.2.1
+sentencepiece==0.2.1
+types-toml==0.10.8.20260518
+wcwidth==0.8.1
+identify==2.6.19
+protobuf==6.33.6
+datasets==3.6.0
+accelerate==1.14.0
+networkx==3.6.1
+pydantic==2.13.4
+multidict==6.7.1
+chardet==7.4.3
+pytest==9.1.0
+babel==2.18.0
+pip==26.1.2
+dill==0.3.8
+referencing==0.37.0
+pre_commit==4.6.0
+numpy==2.4.6
+math-verify==0.9.0
+traitlets==5.15.1
+nvidia-curand-cu12==10.3.7.77
+websocket-client==1.9.0
+hf-xet==1.5.1
+unidiff==0.7.5
+nest-asyncio2==1.7.2
+typing_extensions==4.15.0
+platformdirs==4.10.0
+torch==2.7.1
+tblib==3.2.2
+sqlfluff==4.2.2
+modal==1.5.0
+ipykernel==7.3.0
+msgspec==0.21.1
+virtualenv==21.5.1
+json5==0.14.0
+pathlib_abc==0.5.2
+aiosignal==1.4.0
+moodist==0.5.1
+rpds-py==2026.5.1
+webencodings==0.5.1
+sniffio==1.3.1
+annotated-types==0.7.0
+python-discovery==1.4.2
+scipy==1.17.1
+GitPython==3.1.50
+defusedxml==0.7.1
+nvidia-cufile-cu12==1.11.1.6
+nvidia-nccl-cu12==2.26.2
+sympy==1.14.0
+tinycss2==1.5.1
+soupsieve==2.8.4
+ninja==1.13.0
+python-dotenv==1.2.2
+ghapi==1.0.13
+jupyter_server_terminals==0.5.4
+markdown-it-py==4.2.0
+nbclient==0.11.0
+mpmath==1.3.0
+frozenlist==1.8.0
+Werkzeug==3.1.8
+executing==2.2.1
+gitdb==4.0.12
+setuptools==82.0.1
+Flask==3.1.1
+MarkupSafe==3.0.3
+notebook==7.5.7
+jupyter_core==5.9.1
+jedi==0.20.0
+mdurl==0.1.2
+lark==1.3.1
+bleach==6.4.0
+hpack==4.1.0
+google-re2==1.1.20240702
+beautifulsoup4==4.15.0
+jsonschema==4.26.0
+psutil==7.2.2
+nvidia-cuda-nvrtc-cu12==12.6.77
+narwhals==2.22.1
+lxml==6.1.1
+fastjsonschema==2.21.2
+tornado==6.5.7
+nodeenv==1.10.0
+typing-inspection==0.4.2
+httpx==0.28.1
+distro==1.9.0
+colorama==0.4.6
+jupyter-console==6.6.3
+jupyterlab_widgets==3.0.16
+PyYAML==6.0.3
+fsspec==2025.3.0
+hyperframe==6.1.0
+nvidia-cuda-cupti-cu12==12.6.80
+charset-normalizer==3.4.7
+wandb==0.27.2
+nbformat==5.10.4
+nvidia-cudnn-cu12==9.5.1.17
+peft==0.19.1
+pathspec==1.1.1
+matplotlib-inline==0.2.2
+huggingface_hub==0.36.2
+pyarrow==24.0.0
+nvidia-cusparse-cu12==12.5.4.2
+cwm==0.0.1
+prompt_toolkit==3.0.52
+omegaconf==2.4.0.dev4
+tiktoken==0.13.0
+comm==0.2.3
+threadpoolctl==3.6.0
+pydantic_core==2.46.4
+tenacity==9.1.4
+parso==0.8.7
+pandas==3.0.3
+webcolors==25.10.0
+idna==3.18
+terminado==0.18.1
+pandocfilters==1.5.1
+aiohttp==3.14.1
+arrow==1.4.0
+packaging==26.2
+tzdata==2026.2
+distlib==0.4.3
+Send2Trash==2.1.0
+jupyterlab_pygments==0.3.0
+decorator==5.3.1
+jupyter_server==2.20.0
+scikit-learn==1.9.0
+six==1.17.0
+diff_cover==10.3.0
+pycparser==3.0
+types-certifi==2021.10.8.3
+toml==0.10.2
+stack-data==0.6.3
+fastcore==1.13.5
+filelock==3.29.4
+xxhash==3.7.0
+pexpect==4.9.0
+jupyter_client==8.9.1
+jiter==0.15.0
+debugpy==1.8.21
+universal_pathlib==0.3.10
+joblib==1.5.3

checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug-core.log

@@ -0,0 +1,15 @@
+{"time":"2026-06-19T14:15:27.301398896+02:00","level":"INFO","msg":"main: starting server","port-filename":"/local/tmp.6767617/tmpgyti6bop/port-599607.txt","pid":599607,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-06-19T14:15:27.302028933+02:00","level":"INFO","msg":"server: will exit if parent process dies","ppid":599607}
+{"time":"2026-06-19T14:15:27.301999053+02:00","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/local/tmp.6767617/wandb-599607-599718-3625508308/socket","Net":"unix"}}
+{"time":"2026-06-19T14:15:27.485481018+02:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-06-19T14:15:27.49441811+02:00","level":"INFO","msg":"handleInformInit: received","streamId":"f7zbl5g6","id":"1(@)"}
+{"time":"2026-06-19T14:15:27.618170162+02:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"f7zbl5g6","id":"1(@)"}
+{"time":"2026-06-19T17:06:21.276182437+02:00","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
+{"time":"2026-06-19T17:06:21.28047003+02:00","level":"INFO","msg":"server is shutting down"}
+{"time":"2026-06-19T17:06:21.280507216+02:00","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
+{"time":"2026-06-19T17:06:21.280596484+02:00","level":"INFO","msg":"server: listener closed","addr":{"Name":"/local/tmp.6767617/wandb-599607-599718-3625508308/socket","Net":"unix"}}
+{"time":"2026-06-19T17:06:21.280545814+02:00","level":"INFO","msg":"connection: closing","id":"1(@)"}
+{"time":"2026-06-19T17:06:21.281790311+02:00","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
+{"time":"2026-06-19T17:06:21.282648474+02:00","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
+{"time":"2026-06-19T17:06:21.282654653+02:00","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
+{"time":"2026-06-19T17:06:21.282659444+02:00","level":"INFO","msg":"server is closed"}

checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug-internal.log

@@ -0,0 +1,15 @@
+{"time":"2026-06-19T14:15:27.495513616+02:00","level":"INFO","msg":"wandb-core"}
+{"time":"2026-06-19T14:15:27.495530857+02:00","level":"INFO","msg":"stream: starting","core version":"0.27.2"}
+{"time":"2026-06-19T14:15:27.616112226+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-06-19T14:15:27.616134112+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-06-19T14:15:27.616150216+02:00","level":"INFO","msg":"stream: created new stream","id":"f7zbl5g6"}
+{"time":"2026-06-19T14:15:27.616287718+02:00","level":"INFO","msg":"handler: started"}
+{"time":"2026-06-19T14:15:27.618163388+02:00","level":"INFO","msg":"stream: started"}
+{"time":"2026-06-19T14:15:27.618208304+02:00","level":"INFO","msg":"writer: started","stream_id":"f7zbl5g6"}
+{"time":"2026-06-19T14:15:27.618225281+02:00","level":"INFO","msg":"sender: started"}
+{"time":"2026-06-19T14:15:27.632535917+02:00","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-06-19T14:15:27.632547267+02:00","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}
+{"time":"2026-06-19T17:06:21.280675611+02:00","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-06-19T17:06:21.281207168+02:00","level":"INFO","msg":"handler: closed"}
+{"time":"2026-06-19T17:06:21.28217981+02:00","level":"INFO","msg":"sender: closed"}
+{"time":"2026-06-19T17:06:21.282191245+02:00","level":"INFO","msg":"stream: all finished"}

checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug.log

@@ -0,0 +1,24 @@
+2026-06-19 14:15:27,122 INFO    MainThread:599607 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
+2026-06-19 14:15:27,122 INFO    MainThread:599607 [wandb_setup.py:_flush():81] Configure stats pid to 599607
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_init.py:setup_run_log_directory():723] Logging user logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug.log
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to model_weights/sft-coder-1.5b/wandb/offline-run-20260619_141527-f7zbl5g6/logs/debug-internal.log
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_init.py:init():766] calling init triggers
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
+config: {'model': 'model_weights/qwen2.5-coder-1.5b', 'output_dir': 'model_weights/sft-coder-1.5b', 'n_samples': -1, 'max_seq_len': 3072, 'max_frames': -1, 'epochs': 4.0, 'lr': 2e-05, 'batch_size': 1, 'grad_accum': 8, 'max_steps': -1, 'sources': ['mbpp', 'humaneval', 'pyx'], 'cache_dir': 'data/cache/sft_train', '_wandb': {}}
+2026-06-19 14:15:27,123 INFO    MainThread:599607 [wandb_init.py:init():814] starting backend
+2026-06-19 14:15:27,485 INFO    MainThread:599607 [wandb_init.py:init():829] sending inform_init request
+2026-06-19 14:15:27,618 INFO    MainThread:599607 [wandb_init.py:init():834] backend started and connected
+2026-06-19 14:15:27,620 INFO    MainThread:599607 [wandb_init.py:init():904] updated telemetry
+2026-06-19 14:15:27,630 INFO    MainThread:599607 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
+2026-06-19 14:15:27,633 INFO    MainThread:599607 [wandb_init.py:init():972] starting run threads in backend
+2026-06-19 14:15:27,924 INFO    MainThread:599607 [wandb_run.py:_console_start():2523] atexit reg
+2026-06-19 14:15:27,924 INFO    MainThread:599607 [wandb_run.py:_redirect():2373] redirect: wrap_raw
+2026-06-19 14:15:27,924 INFO    MainThread:599607 [wandb_run.py:_redirect():2442] Wrapping output streams.
+2026-06-19 14:15:27,924 INFO    MainThread:599607 [wandb_run.py:_redirect():2465] Redirects installed.
+2026-06-19 14:15:27,928 INFO    MainThread:599607 [wandb_init.py:init():1010] run started, returning control to user process
+2026-06-19 14:15:33,043 INFO    MainThread:599607 [wandb_run.py:_config_callback():1346] config_cb None None {'vocab_size': 151676, 'max_position_embeddings': 32768, 'hidden_size': 1536, 'intermediate_size': 8960, 'num_hidden_layers': 28, 'num_attention_heads': 12, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 28, 'num_key_value_heads': 2, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'rope_theta': 1000000.0, 'rope_scaling': None, 'attention_dropout': 0.0, 'layer_types': ['full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention', 'full_attention'], 'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'dtype': 'bfloat16', 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'architectures': ['Qwen2ForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 151643, 'eos_token_id': 151643, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '_name_or_path': 'model_weights/qwen2.5-coder-1.5b', 'transformers_version': '4.57.6', 'model_type': 'qwen2', 'tf_legacy_loss': False, 'use_bfloat16': False, 'output_attentions': False, 'output_dir': 'model_weights/sft-coder-1.5b', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 8, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 4.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': 'model_weights/sft-coder-1.5b/runs/Jun19_14-15-27_alvis4-37', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 5, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'project': 'huggingface', 'trackio_space_id': 'trackio', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': {'use_reentrant': False}, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'liger_kernel_config': None, 'eval_use_gather_object': False, 'average_tokens_across_devices': True}
+2026-06-19 14:15:33,047 INFO    MainThread:599607 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 1543314944 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x145bcdaf6ad0>>
+2026-06-19 14:15:33,047 INFO    MainThread:599607 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 1543314944 None
+2026-06-19 17:06:21,276 INFO    wandb-AsyncioManager-main:599607 [service_client.py:_forward_responses():122] Reached EOF.
+2026-06-19 17:06:21,276 INFO    wandb-AsyncioManager-main:599607 [mailbox.py:close():154] Closing mailbox, abandoning 0 handles.

checkpoints/sft1.5b_lr1e5_bs32/wandb/offline-run-20260619_141527-f7zbl5g6/run-f7zbl5g6.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b29b895bc295fe58e4fb463eb712323f657e88d5e5fe462466c7c703fc01c0
+size 3637022