Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb1045a6588100f77da2fc367c78dce331d79e23ec98420f4290693e5657de94
+oid sha256:2742f1aa9af0a5c8fe54598a680690e77befd687f6ca7f1e39a7f423b59ca9cf
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f72f392d6528b4317aef9fefb0c2d13f84965b56617fbc00a465411e33a0ab1
-size 60386772
+oid sha256:448434462df3f3af483e599a4676d68fe53f423ca3787e848a18dd521a2b54d2
+size 60387220

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d87e9c1f179372f9242367ad770c30c7bd7eeb48af101c530d591d3c29dd85
+oid sha256:c22b464bb859e79260348791ff89706887d2ac8a613c40a3bf13d707af961dcf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b00c955337268a520a0035ea66591799a038b74d25acad9619f1a1a47155f3ce
+oid sha256:5f5a4b25c902770d977f31c26bd7fcb65734842e202b09426810a9afa34c40d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015338364316829254,
+  "epoch": 0.018406037180195105,
   "eval_steps": 20,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,51 @@
       "eval_samples_per_second": 5.073,
       "eval_steps_per_second": 0.659,
       "step": 240
+    },
+    {
+      "epoch": 0.015951898889502422,
+      "grad_norm": 0.7300752997398376,
+      "learning_rate": 0.00019895688456189153,
+      "loss": 1.669,
+      "step": 260
+    },
+    {
+      "epoch": 0.015951898889502422,
+      "eval_loss": 1.5231231451034546,
+      "eval_runtime": 19.522,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 0.666,
+      "step": 260
+    },
+    {
+      "epoch": 0.017178968034848762,
+      "grad_norm": 0.7053245306015015,
+      "learning_rate": 0.00019887507158635362,
+      "loss": 1.6513,
+      "step": 280
+    },
+    {
+      "epoch": 0.017178968034848762,
+      "eval_loss": 1.514104962348938,
+      "eval_runtime": 19.6874,
+      "eval_samples_per_second": 5.079,
+      "eval_steps_per_second": 0.66,
+      "step": 280
+    },
+    {
+      "epoch": 0.018406037180195105,
+      "grad_norm": 0.8148968815803528,
+      "learning_rate": 0.00019879325861081568,
+      "loss": 1.5712,
+      "step": 300
+    },
+    {
+      "epoch": 0.018406037180195105,
+      "eval_loss": 1.4980120658874512,
+      "eval_runtime": 19.7232,
+      "eval_samples_per_second": 5.07,
+      "eval_steps_per_second": 0.659,
+      "step": 300
     }
   ],
   "logging_steps": 20,
@@ -194,7 +239,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 1.568681283999744e+16,
+  "total_flos": 1.892439319744512e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null