Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e047dba2ebb737e3115d6c4fc4e168cfc84d58d2f14218f9b7d5efc368421c
+oid sha256:19607b2b2b1fda334b932352f9c2a21bf6adcf5b66cbcbb2d77a95d401ad664b
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aa9e9ebcc993510239d487b2fd1ca036d65010ab5286f9f15b279f6549b6e97
+oid sha256:2a6189ead67bc1da5a8895d7c856e70d0b015d285b6d709276bc33c267c698a4
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472c208bc38b1ca633c54a92ad0164d9ac8eef7c79516742340b24ee5af4486f
+oid sha256:29c1f92e505a54ea8796e41cbf9824c8d53504b0106ad745c808ec05d73d165e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f794552decd9aa76ab29a20764126af04a4c938707d8fa5c1d538d8352460007
+oid sha256:5256258c422cade61a05f9b7acf2463558d18db9447187b4d8690b3bca3e867f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006580699747739844,
+  "epoch": 0.0012221299531516852,
   "eval_steps": 5,
-  "global_step": 21,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -96,6 +96,72 @@
       "learning_rate": 0.0002,
       "loss": 10.565,
       "step": 21
+    },
+    {
+      "epoch": 0.0007520799711702678,
+      "grad_norm": 4.21265172958374,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 10.1523,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007834166366356955,
+      "eval_loss": 9.9229154586792,
+      "eval_runtime": 130.5123,
+      "eval_samples_per_second": 102.956,
+      "eval_steps_per_second": 51.482,
+      "step": 25
+    },
+    {
+      "epoch": 0.0008460899675665512,
+      "grad_norm": 4.139631271362305,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 9.9544,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009400999639628347,
+      "grad_norm": 3.844069242477417,
+      "learning_rate": 0.0001,
+      "loss": 9.713,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009400999639628347,
+      "eval_loss": 9.596590995788574,
+      "eval_runtime": 130.3595,
+      "eval_samples_per_second": 103.076,
+      "eval_steps_per_second": 51.542,
+      "step": 30
+    },
+    {
+      "epoch": 0.0010341099603591183,
+      "grad_norm": 3.5350520610809326,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 9.5719,
+      "step": 33
+    },
+    {
+      "epoch": 0.0010967832912899737,
+      "eval_loss": 9.454024314880371,
+      "eval_runtime": 130.2285,
+      "eval_samples_per_second": 103.18,
+      "eval_steps_per_second": 51.594,
+      "step": 35
+    },
+    {
+      "epoch": 0.0011281199567554016,
+      "grad_norm": 2.883392095565796,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 9.4912,
+      "step": 36
+    },
+    {
+      "epoch": 0.0012221299531516852,
+      "grad_norm": 2.996534824371338,
+      "learning_rate": 0.0,
+      "loss": 9.4766,
+      "step": 39
     }
   ],
   "logging_steps": 3,
@@ -110,12 +176,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2850699608064.0,
+  "total_flos": 5294156414976.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null