Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
     "up_proj",
     "k_proj",
-    "q_proj",
-    "o_proj",
-    "down_proj",
-    "gate_proj"
+    "v_proj",
+    "o_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 sha256:8714bdd575f698538e566cbec079e4500732a829cbe5d7479e7c979fa8fbd980
+oid sha256:f065171b9c2a941c6db6887c2df56e9eee64324358f8691b407e62fcc4d6ce48
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa5a3f4d6e84b321af019c36c54d78dd9fd5fdb30cba819cdbe88e60e0513439
+oid sha256:3e5cbdd9136cc98a2e40352614a0df30f74b821b277012e2e8f39f31fb4da3b4
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2f2b1fe1ee433d0949425d85cbc1e7db562c93cb1fc4f9c675368fbffc7b15d
+oid sha256:8584eb0606268fe40a7b607403caf1bbfdb0ed83707fc0a067fb7329a1dc8581
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00020296326364927948,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.002638522427440633,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.00020296326364927948,
       "eval_loss": 3.347236156463623,
-      "eval_runtime": 62.4654,
-      "eval_samples_per_second": 33.218,
-      "eval_steps_per_second": 16.617,
+      "eval_runtime": 61.3527,
+      "eval_samples_per_second": 33.821,
+      "eval_steps_per_second": 16.919,
       "step": 1
+    },
+    {
+      "epoch": 0.0010148163182463973,
+      "grad_norm": 1.6440613269805908,
+      "learning_rate": 5e-05,
+      "loss": 3.3295,
+      "step": 5
+    },
+    {
+      "epoch": 0.0020296326364927946,
+      "grad_norm": 2.3382773399353027,
+      "learning_rate": 0.0001,
+      "loss": 3.1632,
+      "step": 10
+    },
+    {
+      "epoch": 0.0020296326364927946,
+      "eval_loss": 2.92110538482666,
+      "eval_runtime": 61.5328,
+      "eval_samples_per_second": 33.722,
+      "eval_steps_per_second": 16.869,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "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 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 25579197825024.0,
+  "total_flos": 332529571725312.0,
   "train_batch_size": 2,
   "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:b01ff3937f288db5249232fe5b253d06a498d330448906ea5cbf1501d4945774
+oid sha256:f23e9b7c8dd103186e7618a1f9afab8f5f327d45c633d30e85db00e6533f3186
 size 6776