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",
     "dense_h_to_4h",
-    "dense_4h_to_h",
-    "dense"
+    "query_key_value",
+    "dense_4h_to_h"
   ],
   "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:d2b46465ab2798d6ccf7e8ab0181a2c96cec6f4a0f9325d29dd680ebd1111925
+oid sha256:55ab80e5337e67550076522cff350345b25f012f85e40b2c2ee92672ffd8e7cf
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f312f670254fff0acc01f0388e6149204d0aaaab60bf146c2ecb64b4fc30bc6f
+oid sha256:6131249293a5a835c4b500921a54db821ca23df7303a9a7b3cd1c152a32463bb
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd0b17a9c54cdbc30b4e19b03add683abff825b52aca58a8c949823f42ac1f9
+oid sha256:bc25a717cde46c08c6f2b25c22d902a21352877c2c2f24a1e588c664c2c4c3be
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00032198989756696385,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00418586866837053,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.00032198989756696385,
       "eval_loss": 11.110438346862793,
-      "eval_runtime": 54.703,
-      "eval_samples_per_second": 382.484,
-      "eval_steps_per_second": 47.822,
+      "eval_runtime": 54.8041,
+      "eval_samples_per_second": 381.778,
+      "eval_steps_per_second": 47.734,
       "step": 1
+    },
+    {
+      "epoch": 0.0032198989756696385,
+      "grad_norm": 2.317124605178833,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 177.7176,
+      "step": 10
+    },
+    {
+      "epoch": 0.0032198989756696385,
+      "eval_loss": 11.102073669433594,
+      "eval_runtime": 53.4715,
+      "eval_samples_per_second": 391.293,
+      "eval_steps_per_second": 48.923,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 241120051200.0,
+  "total_flos": 3337101508608.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bf52790b09a5ed5efa848aaa53f5593daf1bbfa3a54dd60162d38dac8552870
+oid sha256:a3d2fae644ebb94f07878b5711a048d07f981eb785d45827d944f0b9539d5330
 size 6776