Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "gate_proj",
     "k_proj",
-    "q_proj",
+    "gate_proj",
+    "v_proj",
     "up_proj",
     "down_proj",
-    "v_proj"
+    "o_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 sha256:7ddd0461d5bf755259516709f3d8b5c8dfc8d055130bd92c9fa5825bc77a7b4a
+oid sha256:47ca939b35ac1ab53327c18731a6cd44a4bcc05702518243ab607fbfa141c1fd
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f904125c16819777f45ebfa59ae7a939eca7b4994a2e4ba06a208a8e26b58416
+oid sha256:1545d35069b142acb5556cceb6513031b2b35788d8c3f8557ef5665f59739664
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:73cc263222070a2aecae10b77475cbc51017c3447299816a4d37b47a38d06607
 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": 0.00030781069642170063,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.004001539053482109,
+  "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": 0.00030781069642170063,
       "eval_loss": 3.4841344356536865,
-      "eval_runtime": 97.7912,
-      "eval_samples_per_second": 13.989,
-      "eval_steps_per_second": 6.994,
+      "eval_runtime": 98.3902,
+      "eval_samples_per_second": 13.904,
+      "eval_steps_per_second": 6.952,
       "step": 1
+    },
+    {
+      "epoch": 0.0015390534821085034,
+      "grad_norm": 1.2541712522506714,
+      "learning_rate": 5e-05,
+      "loss": 3.3695,
+      "step": 5
+    },
+    {
+      "epoch": 0.0030781069642170067,
+      "grad_norm": 1.8117327690124512,
+      "learning_rate": 0.0001,
+      "loss": 3.1959,
+      "step": 10
+    },
+    {
+      "epoch": 0.0030781069642170067,
+      "eval_loss": 2.695909261703491,
+      "eval_runtime": 99.0664,
+      "eval_samples_per_second": 13.809,
+      "eval_steps_per_second": 6.904,
+      "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": 184956424814592.0,
+  "total_flos": 2496911734996992.0,
   "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 sha256:4db8d3ded84493eaa45fca4685296107e950a1dffcd4a83a65798652bbdf8b15
+oid sha256:384e1517fd70b35723a6db1813ccc3bda026c8681d80534c90d0350876bb4c64
 size 6776