Training in progress, step 2140, checkpoint

last-checkpoint/README.md

@@ -1,6 +1,6 @@
 ---
-library_name: peft
 base_model: Qwen/Qwen2-1.5B
+library_name: peft
 ---
 
 # Model Card for Model ID

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "q_proj",
     "up_proj",
-    "gate_proj",
-    "k_proj",
     "o_proj",
-    "v_proj",
-    "down_proj"
+    "down_proj",
+    "gate_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4b48605b7908c6c3cb92661a446438803c1acd9c09849363fbd525f536e574
+oid sha256:38884bc58b7c52d3509a18f60f5efea83a5bde97636fa32698123e97f400b068
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fadc7ddaa7c8d0042358e2a5baa607920153a3514ff6ac69482a291d9a05ddda
+oid sha256:32b7915bc7d763bf184c8f2b905a341109f68c87052746fd8e0b71c3cb2937b6
 size 75455810

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d443a2e4e38986fdfbce09bb15fb1f520183aec59744ce156f4604030fd8c589
+oid sha256:7756ad94464bbc08a1b2da3642d6832bdcbfd9676937bf3e7d8f04d4c073525d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7461be29c782b65290c8ea4037877ee044396194b7fab404fd344a9cb3ecddbe
+oid sha256:2c7a16cdf8597b5e5c4a6a21bfd0275f94817a43b3d144343e9c35d3d891885a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8276450796062897,
+  "epoch": 0.8291949767591106,
   "eval_steps": 500,
-  "global_step": 2136,
+  "global_step": 2140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14959,6 +14959,34 @@
       "learning_rate": 7.420021516934539e-07,
       "loss": 1.3736,
       "step": 2136
+    },
+    {
+      "epoch": 0.828032553894495,
+      "grad_norm": 0.18238689005374908,
+      "learning_rate": 7.387483192208627e-07,
+      "loss": 1.4007,
+      "step": 2137
+    },
+    {
+      "epoch": 0.8284200281827002,
+      "grad_norm": 0.18637992441654205,
+      "learning_rate": 7.355010676095459e-07,
+      "loss": 1.4034,
+      "step": 2138
+    },
+    {
+      "epoch": 0.8288075024709054,
+      "grad_norm": 0.18678662180900574,
+      "learning_rate": 7.322604018743923e-07,
+      "loss": 1.3421,
+      "step": 2139
+    },
+    {
+      "epoch": 0.8291949767591106,
+      "grad_norm": 0.19561077654361725,
+      "learning_rate": 7.290263270201231e-07,
+      "loss": 1.3741,
+      "step": 2140
     }
   ],
   "logging_steps": 1.0,
@@ -14978,7 +15006,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1129038541824717e+18,
+  "total_flos": 2.1168976479065395e+18,
   "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 sha256:49dea52e1d61dbd79df39995bfc2d249effcfaf6fef1e8cdf486950bfe864a05
+oid sha256:0c4386e79026127651aadb56025eb1882c7820cff5922fb5a0636ad098d66e40
 size 5560