Training in progress, step 80, checkpoint

checkpoint-80/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: Qwen/Qwen2.5-1.5B
+base_model: Qwen/Qwen3-0.6B-Base
 library_name: peft
 ---
 

checkpoint-80/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B",
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B-Base",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "q_proj",
     "v_proj",
     "gate_proj",
-    "up_proj",
     "down_proj",
     "o_proj",
-    "q_proj"
+    "k_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-80/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2171570d9bd7dd751f84ffc063a29d16bb985b6da7b54fd5791ffcf7f631c67
-size 147770496
+oid sha256:704aa895f2f07026040c80aabf199a59a516b3812a5f621b843a6d90d51efef1
+size 80792456

checkpoint-80/added_tokens.json

@@ -1,6 +1,10 @@
 {
+  "</think>": 151668,
   "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
   "<tool_call>": 151657,
+  "<tool_response>": 151665,
   "<|box_end|>": 151649,
   "<|box_start|>": 151648,
   "<|endoftext|>": 151643,

checkpoint-80/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c144d6a2e0021236496a3f677b3883ef3f1949de5af7aba3102df0fa925d563
-size 295765866
+oid sha256:16cead893f86861710de22e991845205a6d4b679b7565f4eaec58cde24be7b9e
+size 161810474

checkpoint-80/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae4fbbc5ce9ed472f995338a1195c12ba1eb2aa7dc11ee2ebdfebb350e98349
+oid sha256:1a29189bdfdfa8f4556c761fea884eb42e375a1a4105f9506a8b8d7fa7ff34f8
 size 1064

checkpoint-80/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-80/tokenizer_config.json

@@ -177,6 +177,38 @@
       "rstrip": false,
       "single_word": false,
       "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "additional_special_tokens": [

checkpoint-80/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09397944199706314,
+  "epoch": 0.18812463256907702,
   "eval_steps": 500,
   "global_step": 80,
   "is_hyper_param_search": false,
@@ -10,67 +10,67 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.011747430249632892,
-      "grad_norm": 1.5699902772903442,
-      "learning_rate": 0.00027,
-      "loss": 3.0983,
+      "epoch": 0.023515579071134628,
+      "grad_norm": 2.4936752319335938,
+      "learning_rate": 6.75e-05,
+      "loss": 3.3727,
       "step": 10
     },
     {
-      "epoch": 0.023494860499265784,
-      "grad_norm": 1.6029695272445679,
-      "learning_rate": 0.00029991523567092526,
-      "loss": 2.062,
+      "epoch": 0.047031158142269255,
+      "grad_norm": 1.268250823020935,
+      "learning_rate": 0.0001425,
+      "loss": 2.4747,
       "step": 20
     },
     {
-      "epoch": 0.03524229074889868,
-      "grad_norm": 1.593436360359192,
-      "learning_rate": 0.00029962234616583063,
-      "loss": 1.2074,
+      "epoch": 0.07054673721340388,
+      "grad_norm": 0.7520093321800232,
+      "learning_rate": 0.00021749999999999997,
+      "loss": 1.6981,
       "step": 30
     },
     {
-      "epoch": 0.04698972099853157,
-      "grad_norm": 0.5851414799690247,
-      "learning_rate": 0.00029912069357315393,
-      "loss": 0.888,
+      "epoch": 0.09406231628453851,
+      "grad_norm": 0.7805754542350769,
+      "learning_rate": 0.00029249999999999995,
+      "loss": 1.1544,
       "step": 40
     },
     {
-      "epoch": 0.05873715124816446,
-      "grad_norm": 0.25992292165756226,
-      "learning_rate": 0.0002984109778320875,
-      "loss": 0.7685,
+      "epoch": 0.11757789535567313,
+      "grad_norm": 0.3181486427783966,
+      "learning_rate": 0.0002999904831331692,
+      "loss": 0.889,
       "step": 50
     },
     {
-      "epoch": 0.07048458149779736,
-      "grad_norm": 0.21082307398319244,
-      "learning_rate": 0.00029749418918542057,
-      "loss": 0.7096,
+      "epoch": 0.14109347442680775,
+      "grad_norm": 0.1686788648366928,
+      "learning_rate": 0.00029995758687228834,
+      "loss": 0.765,
       "step": 60
     },
     {
-      "epoch": 0.08223201174743025,
-      "grad_norm": 0.16843102872371674,
-      "learning_rate": 0.0002963716067978866,
-      "loss": 0.6901,
+      "epoch": 0.1646090534979424,
+      "grad_norm": 0.16962774097919464,
+      "learning_rate": 0.000299901198877339,
+      "loss": 0.7138,
       "step": 70
     },
     {
-      "epoch": 0.09397944199706314,
-      "grad_norm": 0.12076722830533981,
-      "learning_rate": 0.000295044796971387,
-      "loss": 0.6702,
+      "epoch": 0.18812463256907702,
+      "grad_norm": 0.1931052953004837,
+      "learning_rate": 0.0002998213279818309,
+      "loss": 0.6962,
       "step": 80
     }
   ],
   "logging_steps": 10,
-  "max_steps": 851,
+  "max_steps": 2550,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 40,
+  "num_train_epochs": 6,
+  "save_steps": 80,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -83,8 +83,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.69525812326826e+17,
-  "train_batch_size": 2,
+  "total_flos": 1.1592700847456256e+17,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-80/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c61b7597101ee42620ee3c35211c8aaa2dd701dc84ac03219baa5f43c59a2eff
+oid sha256:db4ff7073a4da3309636bbb72b82f1473dd3f796afe5e7d3e7687cadcf17ca0f
 size 5688