Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_4h_to_h",
     "dense_h_to_4h",
     "dense",
-    "query_key_value"
+    "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:d07c57f13d119d8e439aca5253f98a671ad033e1bce43e0830d64c7a33badfa7
+oid sha256:3f8788c7ba1b3708d8b9d2d24f9400c8687d847a1168624521ee9a80ff0ec0f8
 size 1579352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa999102a04d02cbc75d2eb64301ddf3da26b2648210b6320cd57048bbdea3f4
+oid sha256:432178a9c24ade79aed7f58d6321c98cb9e7b75b033581f285d3cc25d43e7a43
 size 857338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8acd9c3c7698950a48d8431d4b8df7966f76aeab635bf20e8211f02589c5202
+oid sha256:5bc19a4842607baf2e8a53b587ac93b0ad0799a675fee8bc9a349e96740a81aa
 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": 0.0003800114003420103,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.004940148204446134,
+  "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": 0.0003800114003420103,
       "eval_loss": 23.27000617980957,
-      "eval_runtime": 9.3049,
-      "eval_samples_per_second": 119.077,
-      "eval_steps_per_second": 59.538,
+      "eval_runtime": 9.2402,
+      "eval_samples_per_second": 119.911,
+      "eval_steps_per_second": 59.956,
       "step": 1
+    },
+    {
+      "epoch": 0.0019000570017100513,
+      "grad_norm": 519.7586669921875,
+      "learning_rate": 5e-05,
+      "loss": 87.194,
+      "step": 5
+    },
+    {
+      "epoch": 0.0038001140034201026,
+      "grad_norm": 664.9725952148438,
+      "learning_rate": 0.0001,
+      "loss": 92.1238,
+      "step": 10
+    },
+    {
+      "epoch": 0.0038001140034201026,
+      "eval_loss": 23.24598503112793,
+      "eval_runtime": 7.9253,
+      "eval_samples_per_second": 139.805,
+      "eval_steps_per_second": 69.903,
+      "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": 1107497582592.0,
+  "total_flos": 14397468573696.0,
   "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 sha256:33d26dbd6b24b7200bff36db3b4f4539fe7f20616d625383a92bb5dbfdab3960
+oid sha256:99adbff461b2e90ed387397c1c81d68feeb74a4c2eb648c9a4615512362ec5ac
 size 6776