Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "dense_4h_to_h",
-    "dense_h_to_4h",
+    "dense",
     "query_key_value",
-    "dense"
+    "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:ab8fd534b99841c2633a7da578aae61e6ad9c2d30a4f496026c77505734454fc
+oid sha256:64ff34582062977f3c069cf9232e70bc9ceebdb1becabc4774ec69e645867fd8
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab44cf6fde6cf374c9fb56cc529eb4a643bd2c223a4fd9cc926a11c28859e69
+oid sha256:b9ac6dde78d076ed41c5bfd870ea5e269d825636c0fe294a1a1d9b13172ee3eb
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b78f5518cedba787787cb66fdb8dc9153feef900a07f6153a2dbab3f3b8f6140
+oid sha256:9f62d06be63aea6e43f7a7172ceba715b15573f70eb3c92388f20ca02c24dcde
 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": 5.236698785085882e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0006807708420611646,
+  "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": 5.236698785085882e-05,
       "eval_loss": 11.104299545288086,
-      "eval_runtime": 62.579,
-      "eval_samples_per_second": 128.494,
-      "eval_steps_per_second": 64.255,
+      "eval_runtime": 62.8672,
+      "eval_samples_per_second": 127.905,
+      "eval_steps_per_second": 63.96,
       "step": 1
+    },
+    {
+      "epoch": 0.0002618349392542941,
+      "grad_norm": 0.9558674693107605,
+      "learning_rate": 5e-05,
+      "loss": 44.4239,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005236698785085882,
+      "grad_norm": 1.087439775466919,
+      "learning_rate": 0.0001,
+      "loss": 44.3971,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005236698785085882,
+      "eval_loss": 11.095877647399902,
+      "eval_runtime": 60.5523,
+      "eval_samples_per_second": 132.794,
+      "eval_steps_per_second": 66.405,
+      "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": 19289604096.0,
+  "total_flos": 250764853248.0,
   "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 sha256:353d30bf5aa29db60fd5cd76f2b44749ddb7e6a4a6ed110bb1da514dd5ed5c39
+oid sha256:aec830eb946bd99d1d30e23af06e5419396ecc9d13d573b20b8f0b4d79902e6a
 size 6776