Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:933b83e5309455a9e82c7d518d9f5720528652e8d34b1f47cfd6ea9a455a4705
+oid sha256:f0a216cebbe63d1a512631b2935fb5dcd970aa5610b15b354e300998ee1bc0f6
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0349802f4a690b33f7004ef186d21ca1cf6f8c45ad1bfdb7f8d4a512f8a0b41f
+oid sha256:6e9616c725a84aceb9183e22859628b58479f9b3b17f642338d39ebd24a1f5f7
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a44e67e7afe750fe86df1f191491956aa5374ed00de2fe34a89e159730d72861
+oid sha256:36f0d7161dd9ad8e601b265301b55ba4312cb15819580d045ab5f9b066af22db
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2742822170257568,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.2677264213562012,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 1.2,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "eval_samples_per_second": 15.303,
       "eval_steps_per_second": 1.919,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 1.0957,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.2677264213562012,
+      "eval_runtime": 126.1088,
+      "eval_samples_per_second": 15.304,
+      "eval_steps_per_second": 1.919,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.836263099222835e+16,
+  "total_flos": 3.1897626964783104e+16,
   "trial_name": null,
   "trial_params": null
 }