Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "query_key_value",
     "dense_4h_to_h",
-    "dense_h_to_4h",
     "dense",
-    "query_key_value"
+    "dense_h_to_4h"
   ],
   "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 sha256:6b492daa54ca85be48d95310db1c4f281ba0d2d035198882d41347418bc8e83b
+oid sha256:04094d66699a20b6a5fd64a50794e38b89dc2cd62d0d9b000592ca1d4f0ccc00
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:876c655c193fb6912eb98c0fc8c1908f82a54363f698f1f7cf3075429f766022
+oid sha256:a817ab6412a20062655f852566d46b068ed478fb4397217d871b8798688486d5
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77bba18256fafda32f39805d8a79bd94ed0adb267c51253610b58903e54ff6d3
+oid sha256:adc65900b1800458289c8c21bab3eeedd0bb320c47305aa0de9c35ef282f5293
 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": 2.3280176929344664e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0003026423000814806,
+  "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": 2.3280176929344664e-05,
       "eval_loss": NaN,
-      "eval_runtime": 81.5983,
-      "eval_samples_per_second": 221.659,
-      "eval_steps_per_second": 110.836,
+      "eval_runtime": 80.0382,
+      "eval_samples_per_second": 225.98,
+      "eval_steps_per_second": 112.996,
       "step": 1
+    },
+    {
+      "epoch": 0.00011640088464672332,
+      "grad_norm": 1.1555752754211426,
+      "learning_rate": 5e-05,
+      "loss": 81.231,
+      "step": 5
+    },
+    {
+      "epoch": 0.00023280176929344664,
+      "grad_norm": 1.4119420051574707,
+      "learning_rate": 0.0001,
+      "loss": 70.7834,
+      "step": 10
+    },
+    {
+      "epoch": 0.00023280176929344664,
+      "eval_loss": NaN,
+      "eval_runtime": 78.0869,
+      "eval_samples_per_second": 231.626,
+      "eval_steps_per_second": 115.82,
+      "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": 747110400.0,
+  "total_flos": 10085990400.0,
   "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 sha256:88ac11f7e368e447f67b8275396974f71ae017dcf649cbc24b7a2c53b3015e1c
+oid sha256:1f9b87c3001562e36f829965594dfc0f789c6b0581b153565cb7d002994f45e3
 size 6776