Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
-    "q_proj",
     "gate_proj",
-    "v_proj",
     "o_proj",
+    "up_proj",
     "down_proj",
-    "up_proj"
+    "q_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 sha256:79b66b8eb63555e042416e158fcc650028bbcf6efedee5341bb88041cd80ed60
+oid sha256:6d50a6790ba12c474e52994cb13542cdab301bc659aeb8de41be4eed68340fb5
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:528b75cc26ae9ebc9cd003db7d223d2b0a88fdbc48e218e9f33e6d309d1d98de
+oid sha256:6abda77a7211f0e6875f06d9ec82211ded15d12733ff5b40088e4c527b212d63
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106d2362bc2f5d0877cb3549f0a8edc5f2a3f7ece3ea2591042b0fa260c47153
+oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006633499170812604,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.08623548922056384,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.006633499170812604,
       "eval_loss": 11.932214736938477,
-      "eval_runtime": 6.111,
-      "eval_samples_per_second": 166.257,
-      "eval_steps_per_second": 20.782,
+      "eval_runtime": 6.0784,
+      "eval_samples_per_second": 167.149,
+      "eval_steps_per_second": 20.894,
       "step": 1
+    },
+    {
+      "epoch": 0.06633499170812604,
+      "grad_norm": 0.003583765821531415,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 11.9322,
+      "step": 10
+    },
+    {
+      "epoch": 0.06633499170812604,
+      "eval_loss": 11.932164192199707,
+      "eval_runtime": 6.074,
+      "eval_samples_per_second": 167.269,
+      "eval_steps_per_second": 20.909,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3663003648.0,
+  "total_flos": 48446177280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37fadeff5bf2c1ad2fb2f2818ec119ef0868c8a2d9b34e4d45229303b9a49639
+oid sha256:8121764773fed7120e6c5873eb165200750ce2f1ba42fa18b53fe7b89c4eee97
 size 6776