Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9507bdc00de6b8bf6bcf3cffc9b8286a9b2f01af0cfbf06ebe07cfa8e1bbdfcb
+oid sha256:1beab8a142209279319747b6b52a644878e34c29d25b9e98e993815e07f89a56
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d53faada5d58b49de6987026f351429387f9118f7ab91764b18b69fa9a1e7a84
+oid sha256:1d9a6e37810aa411da4aca5be45f1c9eabb94161e9bba7e3b1f1cff4f4295636
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed7f123f90fb83f4b017b98f14cda47d3186330fc9c73ef98103c3480c267bfc
+oid sha256:e73923f37ec7135161905afe711e033d5580982c1091005b6796522a09e1da71
 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": 0.9479925036430359,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.4,
+  "best_metric": 0.9420929551124573,
+  "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": 2.434,
       "eval_steps_per_second": 0.305,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 0.7587,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 0.9420929551124573,
+      "eval_runtime": 787.6767,
+      "eval_samples_per_second": 2.45,
+      "eval_steps_per_second": 0.307,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 4.661310169822003e+17,
+  "total_flos": 4.9198271845933056e+17,
   "trial_name": null,
   "trial_params": null
 }