Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232b1f56f6ebf344f5c012b7b3e9af10382c003ca7cd01523fe1aaba0c988ec7
+oid sha256:af6f25c3d100028a7c97b2404463880ba1074f486d30e36f7c8479d72c96d820
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aef14976ac039f712ae953d0ffd5bca65180c1336d98f5b5fb0d60faf6ff01c
+oid sha256:0a0c807c195695ccc9e9ea08b9edc7b6cdd72c4e525eddffcc6882abcbc2ed24
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0ed68540abf53877f31d72dfb49b5e75b15e4cc70f9158d4c016264864ea60a
+oid sha256:9c78706d744471c89dd06ac547d70d23cf235b0473edb572795996232735d747
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
+oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0762122869491577,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.4,
+  "best_metric": 1.0724916458129883,
+  "best_model_checkpoint": "./outputs/checkpoint-1900",
+  "epoch": 2.533333333333333,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,6 +259,20 @@
       "eval_samples_per_second": 5.409,
       "eval_steps_per_second": 0.678,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 0.9215,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 1.0724916458129883,
+      "eval_runtime": 235.9181,
+      "eval_samples_per_second": 8.181,
+      "eval_steps_per_second": 1.026,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.545114966391931e+17,
+  "total_flos": 2.6860284067270656e+17,
   "trial_name": null,
   "trial_params": null
 }