Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "k_proj",
-    "q_proj",
+    "v_proj",
+    "down_proj",
     "o_proj",
+    "q_proj",
     "gate_proj",
-    "up_proj",
-    "v_proj"
+    "up_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 sha256:8255a7c6bf6118835ffbe19e1ff21bc0c90f601294b63befc3a64b1bacc910c5
+oid sha256:5af7b5bc702c1ab35a5640dd809c24209965d0aad3d5f46017c2f92e7826c8c6
 size 2185308208

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59c2fccab1668c472ff608b6eefe40c0d349641112279a54b5575f30a6cd7525
+oid sha256:2e12b2ed32697d36a744a3de88619575b41923b6461f82d017d654c3dee40df6
 size 168037178

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00041043882751308275,
+  "epoch": 0.00020522116856353732,
   "eval_steps": 3,
   "global_step": 6,
   "is_hyper_param_search": false,
@@ -9,69 +9,69 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 6.840647125218046e-05,
-      "grad_norm": 1.2007124423980713,
+      "epoch": 3.420352809392289e-05,
+      "grad_norm": 1.608834147453308,
       "learning_rate": 2e-05,
-      "loss": 2.8063,
+      "loss": 2.8211,
       "step": 1
     },
     {
-      "epoch": 6.840647125218046e-05,
-      "eval_loss": 3.476195812225342,
-      "eval_runtime": 469.3142,
-      "eval_samples_per_second": 13.117,
-      "eval_steps_per_second": 6.559,
+      "epoch": 3.420352809392289e-05,
+      "eval_loss": 3.4762773513793945,
+      "eval_runtime": 495.8449,
+      "eval_samples_per_second": 12.415,
+      "eval_steps_per_second": 12.415,
       "step": 1
     },
     {
-      "epoch": 0.00013681294250436092,
-      "grad_norm": 1.016757607460022,
+      "epoch": 6.840705618784578e-05,
+      "grad_norm": 1.8106151819229126,
       "learning_rate": 4e-05,
-      "loss": 2.3584,
+      "loss": 2.7652,
       "step": 2
     },
     {
-      "epoch": 0.00020521941375654137,
-      "grad_norm": 0.8679972887039185,
+      "epoch": 0.00010261058428176866,
+      "grad_norm": 1.0310214757919312,
       "learning_rate": 6e-05,
-      "loss": 2.565,
+      "loss": 2.0629,
       "step": 3
     },
     {
-      "epoch": 0.00020521941375654137,
-      "eval_loss": 3.4688305854797363,
-      "eval_runtime": 472.1642,
-      "eval_samples_per_second": 13.038,
-      "eval_steps_per_second": 6.519,
+      "epoch": 0.00010261058428176866,
+      "eval_loss": 3.469648838043213,
+      "eval_runtime": 487.5743,
+      "eval_samples_per_second": 12.626,
+      "eval_steps_per_second": 12.626,
       "step": 3
     },
     {
-      "epoch": 0.00027362588500872185,
-      "grad_norm": 0.7447469830513,
+      "epoch": 0.00013681411237569156,
+      "grad_norm": 1.9326692819595337,
       "learning_rate": 8e-05,
-      "loss": 2.2168,
+      "loss": 2.6316,
       "step": 4
     },
     {
-      "epoch": 0.00034203235626090227,
-      "grad_norm": 1.2870368957519531,
+      "epoch": 0.00017101764046961444,
+      "grad_norm": 1.1122183799743652,
       "learning_rate": 0.0001,
-      "loss": 2.9778,
+      "loss": 2.4229,
       "step": 5
     },
     {
-      "epoch": 0.00041043882751308275,
-      "grad_norm": 1.2918143272399902,
+      "epoch": 0.00020522116856353732,
+      "grad_norm": 1.5624297857284546,
       "learning_rate": 0.00012,
-      "loss": 3.1689,
+      "loss": 2.8127,
       "step": 6
     },
     {
-      "epoch": 0.00041043882751308275,
-      "eval_loss": 3.4169740676879883,
-      "eval_runtime": 469.102,
-      "eval_samples_per_second": 13.123,
-      "eval_steps_per_second": 6.561,
+      "epoch": 0.00020522116856353732,
+      "eval_loss": 3.4261391162872314,
+      "eval_runtime": 486.5579,
+      "eval_samples_per_second": 12.652,
+      "eval_steps_per_second": 12.652,
       "step": 6
     }
   ],
@@ -92,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2219478305734656.0,
+  "total_flos": 1109739152867328.0,
   "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 sha256:2d638e8d3c0cc1e7757dcd32106c2914b72f1485e5fa91782585f316d44ddeb6
+oid sha256:ed04e29d3037d87c0defa1a0ab640c5cb173a163f6893e09aa7721b26cfe4d70
 size 6776