Training in progress, epoch 1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7803832bbb135b2e0f33dec6f9c991f5885e75a2deedd28a6ee7c8fcbea2ba2
+oid sha256:36368dfd8991de06598b374b05f2982e3aefedbe4aeac760b8d6b8026242b0de
 size 10108960

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 14,
-  "best_metric": 7.821501731872559,
+  "best_metric": 7.935835361480713,
   "best_model_checkpoint": "qwen2.5-7b-instruct-sft/checkpoint-14",
   "epoch": 2.0,
   "eval_steps": 8,
@@ -11,36 +11,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.010252904989747097,
-      "eval_entropy": 2.023237184474343,
-      "eval_loss": 8.50821304321289,
-      "eval_mean_token_accuracy": 0.33141817387781647,
-      "eval_num_tokens": 10134.0,
-      "eval_runtime": 5.8055,
-      "eval_samples_per_second": 3.273,
-      "eval_steps_per_second": 3.273,
+      "eval_accuracy": 0.014050964515360804,
+      "eval_entropy": 2.0623741275385807,
+      "eval_loss": 8.619595527648926,
+      "eval_mean_token_accuracy": 0.318189589600814,
+      "eval_num_tokens": 10278.0,
+      "eval_runtime": 5.6586,
+      "eval_samples_per_second": 3.358,
+      "eval_steps_per_second": 3.358,
       "step": 7
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.011847801321485534,
-      "eval_entropy": 2.32025314632215,
-      "eval_loss": 7.821501731872559,
-      "eval_mean_token_accuracy": 0.3833909505291989,
-      "eval_num_tokens": 20268.0,
-      "eval_runtime": 5.4711,
-      "eval_samples_per_second": 3.473,
-      "eval_steps_per_second": 3.473,
+      "eval_accuracy": 0.01476542033817576,
+      "eval_entropy": 2.3609655405345715,
+      "eval_loss": 7.935835361480713,
+      "eval_mean_token_accuracy": 0.3734086673510702,
+      "eval_num_tokens": 20556.0,
+      "eval_runtime": 5.4063,
+      "eval_samples_per_second": 3.514,
+      "eval_steps_per_second": 3.514,
       "step": 14
     },
     {
       "epoch": 2.0,
       "step": 14,
-      "total_flos": 942424595324928.0,
-      "train_loss": 9.187333243233818,
-      "train_runtime": 63.3043,
-      "train_samples_per_second": 1.58,
-      "train_steps_per_second": 0.221
+      "total_flos": 955816063819776.0,
+      "train_loss": 9.08677237374442,
+      "train_runtime": 64.7345,
+      "train_samples_per_second": 1.545,
+      "train_steps_per_second": 0.216
     }
   ],
   "logging_steps": 20,
@@ -60,7 +60,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 942424595324928.0,
+  "total_flos": 955816063819776.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a2a2a99dd14f22869563a396717cc0f93677e1ec5284c6dc50ac20ea7c9d57
+oid sha256:5060514daa07d2cc108c95569ab29dbd15d3bf97638012471eb97161866abd71
 size 5752