Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
     "query_key_value",
+    "dense_h_to_4h",
     "dense_4h_to_h",
-    "dense_h_to_4h"
+    "dense"
   ],
   "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 sha256:05daecb89356790595aeecf6241f768e5e0efb0729fbb524f3a695598b0a1cf3
+oid sha256:eab223446d5db613416819f185e3aff516cee7c6adde7c428775d840a8e67f76
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a1aca7f96bb0ba13ed020735a6d33a271ca8a13b16ecb41811d876c44a20e17
+oid sha256:e785916fc14a385a16cdf168c51c55fbb7c652490c1c5098be2c25a4e714d473
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8482585456f64ac9c5e34989d32f4ce51e3b9d3c750ed5faae1f674e6609b1ce
+oid sha256:efda7bb3ffc76cc93358af768939578180f50a5d7a092a14ff250e66573ba3bd
 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": 0.000245368666421298,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.003189792663476874,
+  "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": 0.000245368666421298,
       "eval_loss": 11.092495918273926,
-      "eval_runtime": 12.3868,
-      "eval_samples_per_second": 138.534,
-      "eval_steps_per_second": 69.267,
+      "eval_runtime": 12.3883,
+      "eval_samples_per_second": 138.517,
+      "eval_steps_per_second": 69.259,
       "step": 1
+    },
+    {
+      "epoch": 0.00122684333210649,
+      "grad_norm": 1.5610966682434082,
+      "learning_rate": 5e-05,
+      "loss": 44.3726,
+      "step": 5
+    },
+    {
+      "epoch": 0.00245368666421298,
+      "grad_norm": 1.5065815448760986,
+      "learning_rate": 0.0001,
+      "loss": 44.3545,
+      "step": 10
+    },
+    {
+      "epoch": 0.00245368666421298,
+      "eval_loss": 11.080097198486328,
+      "eval_runtime": 11.7561,
+      "eval_samples_per_second": 145.967,
+      "eval_steps_per_second": 72.984,
+      "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": 16878403584.0,
+  "total_flos": 221830447104.0,
   "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 sha256:15e08e3ea788a08bd2cdb0b8b59208e1f5331c95a13a38fd8a952f9777e49246
+oid sha256:8bc8aacf3d76566348b24427e7ad8e4a279a25dc7be0ffc4c3e240d43a5ea438
 size 6776