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",
-    "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 sha256:66f4f8ab2d4d86f36cf92f0d072caee4fb33857a2708d70cd20dda76a21826af
+oid sha256:cd53bb0bd8065b2924fefb3c4f9f10f9c79ab3b6e447c564be03787729f43e76
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea2fb58fa0ab043e1d824f762d7cb050cce4bd17bb06e16a9a87885f2fc3c1e1
+oid sha256:4571e51898eaccbdfed4859c4cd373d60b56d135d58fbae136becf055330723f
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e1a1220d67625c7f0818e9c3442286fea4c5721e7fd1bd057ffdcbf1f017270
+oid sha256:17f459dc0ff0b8de89db88bfdf5bedfd0c0ef4c576938a039c8c06b9e448f916
 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": 0.00024198427102238354,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.003145795523290986,
+  "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": 0.00024198427102238354,
       "eval_loss": 1.701642632484436,
-      "eval_runtime": 66.5597,
-      "eval_samples_per_second": 26.142,
-      "eval_steps_per_second": 13.071,
+      "eval_runtime": 65.8495,
+      "eval_samples_per_second": 26.424,
+      "eval_steps_per_second": 13.212,
       "step": 1
+    },
+    {
+      "epoch": 0.0012099213551119178,
+      "grad_norm": 1.5044355392456055,
+      "learning_rate": 5e-05,
+      "loss": 6.4975,
+      "step": 5
+    },
+    {
+      "epoch": 0.0024198427102238356,
+      "grad_norm": 1.8346918821334839,
+      "learning_rate": 0.0001,
+      "loss": 6.6052,
+      "step": 10
+    },
+    {
+      "epoch": 0.0024198427102238356,
+      "eval_loss": 1.6462026834487915,
+      "eval_runtime": 65.8084,
+      "eval_samples_per_second": 26.44,
+      "eval_steps_per_second": 13.22,
+      "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": 44785855365120.0,
+  "total_flos": 515037336698880.0,
   "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:daf8845f5660eda6a427f1d8f5ba731b80162d70fcd525458989dd9933159efe
+oid sha256:4e5fa0678a13a5087d4500a1f3a28124c8aca95ecdfb3e9f71ba333fd590170d
 size 6776