Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
-    "up_proj",
     "down_proj",
     "q_proj",
-    "v_proj",
-    "k_proj"
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "up_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 sha256:2a1f9098493b36443ab5b0be13cc8ba69bfb7b6828da2c85b7f93188bf12e4c4
+oid sha256:326b1b845f6e3951d99874a067e42cf1da0a04c271299100f38d39b4162f06ef
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c409f1541fa5413ebc87318d0f229ad2c88fde38687c5d20cd869ddc2ac4c75
+oid sha256:3a70d77138a00cbb65f943adb4add6fe2950097fdd2d62f09437368333625727
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3e24e5a4848112015906f3af8fac3e7620b85d2495d2a8ad5b1d541e67d1036
+oid sha256:c8a7b521d0c0227fdc116c378b46fe46de4fc9e101a32fe62944526f83c1fc8e
 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": 0.001226993865030675,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.015950920245398775,
+  "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": 0.001226993865030675,
       "eval_loss": 0.8833416700363159,
-      "eval_runtime": 23.928,
-      "eval_samples_per_second": 14.376,
-      "eval_steps_per_second": 7.188,
+      "eval_runtime": 23.9331,
+      "eval_samples_per_second": 14.373,
+      "eval_steps_per_second": 7.187,
       "step": 1
+    },
+    {
+      "epoch": 0.006134969325153374,
+      "grad_norm": 2.763533592224121,
+      "learning_rate": 5e-05,
+      "loss": 0.7847,
+      "step": 5
+    },
+    {
+      "epoch": 0.012269938650306749,
+      "grad_norm": 2.2924604415893555,
+      "learning_rate": 0.0001,
+      "loss": 0.6431,
+      "step": 10
+    },
+    {
+      "epoch": 0.012269938650306749,
+      "eval_loss": 0.4092090427875519,
+      "eval_runtime": 24.1287,
+      "eval_samples_per_second": 14.257,
+      "eval_steps_per_second": 7.128,
+      "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": 75014599606272.0,
+  "total_flos": 987692228149248.0,
   "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:d7b4b5a8a698c7f4b10d8d2e690c5464b490ef46062835b5f9f8815c22a6013b
+oid sha256:c3a2141b1103d3b4e06f46bb87d7c1dabef547cba1a49f430162dfdb593cfb3c
 size 6776