Training in progress, step 10, checkpoint

last-checkpoint/README.md

@@ -1,9 +1,9 @@
 ---
-base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
+base_model: unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:unsloth/qwen3-0.6b-unsloth-bnb-4bit
+- base_model:adapter:unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit
 - lora
 - sft
 - transformers

last-checkpoint/adapter_config.json

@@ -3,11 +3,11 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": {
-    "base_model_class": "Qwen3ForCausalLM",
-    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/qwen3-0.6b-unsloth-bnb-4bit",
+  "base_model_name_or_path": "unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -29,17 +29,17 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "v_proj",
-    "q_proj",
     "up_proj",
+    "q_proj",
+    "o_proj",
     "down_proj",
-    "k_proj",
-    "o_proj"
+    "v_proj",
+    "gate_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb6062623c401be6884015d9d22ab9ece656c01498887dc7f6631c1f91a9680f
-size 10143496
+oid sha256:a616e38fa8e78d658c3597cb8b80666469400ae0af05db84f75fda5e1b965d18
+size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8883c090dfea21204dd0d133dfb8a001ddc26f2f19af365b4b15229bff5fc4
-size 5587525
+oid sha256:5ebbbf6734ed4b7059ac474e7fa33d29006da0bced77223d4fd8b701ce4276b3
+size 9572677

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e565c66ba084a67fdcb79187240ebbe9ad2cbca9c083af6e2adf46532b9dba
+oid sha256:2618226506644b44f9acd396cb1169369bfcc3cbedb2e7b2c06a112a3a8cd862
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be4c65680a9815ca3fc0738d3db6d8ea3a0d6246656b7e251a9b34a942fa7e0
+oid sha256:5f573b9f7149922ed73a27c9028f6f2cbdca1c0ef23c998ef777ef3be95e566d
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa048ca0ee89ee1d02a272e194e1481677e88833cfeb958be5aa1219e0a46f44
+oid sha256:f90ad91c82489d458a8723b573e91e4f2e9d0c77a9a58a9022645b90b2afea7d
 size 1465

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7430e9138b76e93fb6f93462394d236b411111aef53cb421ba97d2691040cca
-size 11423114
+oid sha256:6b4360dd6a184650ffc48056c2569bc603f896c5adfe94b10f1c79f809638aa5
+size 11422166

last-checkpoint/tokenizer_config.json

@@ -4,7 +4,7 @@
   "bos_token": null,
   "eos_token": "<|im_end|>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|PAD_TOKEN|>",
+  "pad_token": "<|vision_pad|>",
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null,
   "added_tokens_decoder": {
@@ -183,46 +183,6 @@
       "rstrip": false,
       "normalized": false,
       "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": false
-    },
-    "151669": {
-      "content": "<|PAD_TOKEN|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   }
 }

last-checkpoint/trainer_state.json

@@ -1,46 +1,95 @@
 {
-  "best_global_step": 3,
-  "best_metric": 2.460531234741211,
-  "best_model_checkpoint": "/tmp/checkpoints_/job_18216dc4-3656-47a5-a842-efcd4fb1cf43/checkpoint-3",
+  "best_global_step": 10,
+  "best_metric": 3.068567991256714,
+  "best_model_checkpoint": "/tmp/checkpoints_/job_fa60d36f-e0b6-414f-8ec4-8d27b9463040/checkpoint-10",
   "epoch": 1.0,
   "eval_steps": 50,
-  "global_step": 3,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.47058823529411764,
-      "grad_norm": 1.6245173215866089,
+      "epoch": 0.1,
+      "grad_norm": 4.2067131996154785,
       "learning_rate": 0.0,
-      "loss": 2.405629873275757,
+      "loss": 3.324939250946045,
       "step": 1
     },
     {
-      "epoch": 0.9411764705882353,
-      "grad_norm": 2.1067492961883545,
-      "learning_rate": 1e-05,
-      "loss": 2.6272225379943848,
+      "epoch": 0.2,
+      "grad_norm": 4.331752777099609,
+      "learning_rate": 6e-06,
+      "loss": 3.4889280796051025,
       "step": 2
     },
     {
-      "epoch": 1.0,
-      "grad_norm": 3.507772445678711,
-      "learning_rate": 2e-05,
-      "loss": 3.0384254455566406,
+      "epoch": 0.3,
+      "grad_norm": 3.86865496635437,
+      "learning_rate": 1.2e-05,
+      "loss": 3.312532901763916,
       "step": 3
     },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.405333995819092,
+      "learning_rate": 1.8e-05,
+      "loss": 3.5451769828796387,
+      "step": 4
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.006685256958008,
+      "learning_rate": 2.4e-05,
+      "loss": 3.31204891204834,
+      "step": 5
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.052533149719238,
+      "learning_rate": 3e-05,
+      "loss": 3.3880691528320312,
+      "step": 6
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.28196382522583,
+      "learning_rate": 2.4e-05,
+      "loss": 3.151078224182129,
+      "step": 7
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.2284908294677734,
+      "learning_rate": 1.8e-05,
+      "loss": 3.2133283615112305,
+      "step": 8
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.721409797668457,
+      "learning_rate": 1.2e-05,
+      "loss": 3.000295400619507,
+      "step": 9
+    },
     {
       "epoch": 1.0,
-      "eval_loss": 2.460531234741211,
-      "eval_runtime": 0.8117,
-      "eval_samples_per_second": 4.928,
-      "eval_steps_per_second": 1.232,
-      "step": 3
+      "grad_norm": 2.67348051071167,
+      "learning_rate": 6e-06,
+      "loss": 3.0001535415649414,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.068567991256714,
+      "eval_runtime": 0.3622,
+      "eval_samples_per_second": 13.803,
+      "eval_steps_per_second": 5.521,
+      "step": 10
     }
   ],
   "logging_steps": 1,
-  "max_steps": 3,
+  "max_steps": 10,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 50,
@@ -56,8 +105,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 33495404642304.0,
-  "train_batch_size": 2,
+  "total_flos": 15401254652160.0,
+  "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72acde95f427f5c0caceca3d439bf221e41298f573bef3ae7440a8d707625ea4
+oid sha256:62ef5223b9379a2e2e03f9ae8eb4a1125fbf4b72c2cc943819d449b0935619a3
 size 5777