Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
-    "gate_proj",
     "v_proj",
     "o_proj",
     "k_proj",
-    "q_proj"
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "down_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 sha256:9a2e08092afb1f9e2040c3fee091ff24691346b90d45cb87c393c26f641a0135
+oid sha256:da7c0d5ebb39c97f206a24e74dee12525371687ccdb8adf6e0ae913e3544b423
 size 608249904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58f855f8dcd5cfbe96f57906a356f5a9617e8612334c1870c7d458b85f28e29c
+oid sha256:68dfaaf12cb252a3279eaa7cd7e4a1b5d1fe44a9b0a1cc14d99726aa90b058e6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
 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

@@ -1,27 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6348818389150925e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.000212534639058962,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.6348818389150925e-05,
-      "eval_loss": 10.176109313964844,
-      "eval_runtime": 1633.4924,
-      "eval_samples_per_second": 15.767,
-      "eval_steps_per_second": 7.884,
+      "eval_loss": 9.864830017089844,
+      "eval_runtime": 1629.5514,
+      "eval_samples_per_second": 15.805,
+      "eval_steps_per_second": 7.903,
       "step": 1
+    },
+    {
+      "epoch": 8.174409194575462e-05,
+      "grad_norm": 22.458637237548828,
+      "learning_rate": 5e-05,
+      "loss": 9.4677,
+      "step": 5
+    },
+    {
+      "epoch": 0.00016348818389150924,
+      "grad_norm": 18.819719314575195,
+      "learning_rate": 0.0001,
+      "loss": 7.4993,
+      "step": 10
+    },
+    {
+      "epoch": 0.00016348818389150924,
+      "eval_loss": 4.158893585205078,
+      "eval_runtime": 1632.8948,
+      "eval_samples_per_second": 15.773,
+      "eval_steps_per_second": 7.887,
+      "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": 175267079258112.0,
+  "total_flos": 2278472030355456.0,
   "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 sha256:48a702f0dfc85538e14c4b90ed3b1b451e4b15316149e2faf4e0b5cd29f344ef
+oid sha256:d875d1d9f9c901e1cbe6f841c2158c40c3c994ad76650b739f927fab28b2a696
 size 6776