Training in progress, epoch 1

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: qwen2.5-7b-instruct-sft
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 

adapter_config.json

@@ -25,8 +25,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:823879147a1605629947cab461a947124a367a36e682ed36554f23be97cf351a
+oid sha256:024ce53997fcfcac8b653168ad823f267fecb97d23ae57ab0e2704e796728473
 size 10108960

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 14,
-  "best_metric": 7.935835361480713,
+  "best_metric": 7.769174098968506,
   "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": 0.014050964515360804,
-      "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,
+      "eval_accuracy": 0.011311172668513388,
+      "eval_entropy": 1.995360060742027,
+      "eval_loss": 8.486817359924316,
+      "eval_mean_token_accuracy": 0.3320777494656412,
+      "eval_num_tokens": 10173.0,
+      "eval_runtime": 5.7445,
+      "eval_samples_per_second": 3.308,
+      "eval_steps_per_second": 3.308,
       "step": 7
     },
     {
       "epoch": 2.0,
-      "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,
+      "eval_accuracy": 0.012003693444136657,
+      "eval_entropy": 2.3059515451130115,
+      "eval_loss": 7.769174098968506,
+      "eval_mean_token_accuracy": 0.3835462488626179,
+      "eval_num_tokens": 20346.0,
+      "eval_runtime": 5.4565,
+      "eval_samples_per_second": 3.482,
+      "eval_steps_per_second": 3.482,
       "step": 14
     },
     {
       "epoch": 2.0,
       "step": 14,
-      "total_flos": 955816063819776.0,
-      "train_loss": 9.08677237374442,
-      "train_runtime": 64.7345,
-      "train_samples_per_second": 1.545,
-      "train_steps_per_second": 0.216
+      "total_flos": 946051451375616.0,
+      "train_loss": 9.178882053920201,
+      "train_runtime": 64.9953,
+      "train_samples_per_second": 1.539,
+      "train_steps_per_second": 0.215
     }
   ],
   "logging_steps": 20,
@@ -60,7 +60,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 955816063819776.0,
+  "total_flos": 946051451375616.0,
   "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 sha256:5060514daa07d2cc108c95569ab29dbd15d3bf97638012471eb97161866abd71
+oid sha256:94d8482c3d536c482f9ff6dc3cc5cf37c97b34842af3ea1abd2e8a6ce1ad5ccc
 size 5752