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:b91d095485061cacc52848d009683c2c2de0fe78624fa1db88084e7830c2eb95
+oid sha256:46acb56ce81b9eaa130934ed581f496e538b7cca77114ea1be2f527e65ae8b45
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8202ffaa20a18c9541815411dd29971db77932dba31f55655579cd21c3034d30
+oid sha256:13fcd684a8fbe2c7ab67a043a274177a1562c28e73742210c1567d468d3b4ee1
 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": 1.0760257244110107,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.4,
+  "best_metric": 1.0725194215774536,
+  "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": 10.302,
       "eval_steps_per_second": 1.292,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 0.9215,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 1.0725194215774536,
+      "eval_runtime": 186.9082,
+      "eval_samples_per_second": 10.326,
+      "eval_steps_per_second": 1.295,
+      "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
 }