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:f6a07dc9f6d3b6b6c9fe0e4a09904c62c3262911cbf734454a249beb72130e78
+oid sha256:50d992ba5edf2df73687974a690a79fa8f263ef680c0b437615ccb8fffbeb7b3
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61aceeef314c87236da6bea5ba9bd25e944c12d6a1db9c22b73100f2c67568cf
+oid sha256:940095018d05a25649ffb47da852e89f7555af35b3d08342f9bd3cc29e31f5cc
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e3024b90e00cf4151fee10d610544743e4f135eee8d4c57a1b90111d87f86c
+oid sha256:1f85e4abb78831eb1bde44d2a42765725c100a0771b8e7eee558b5dbbd2981ee
 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": 1.359381914138794,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.3538635969161987,
+  "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": 12.725,
       "eval_steps_per_second": 1.596,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 1.1028,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.3538635969161987,
+      "eval_runtime": 151.6567,
+      "eval_samples_per_second": 12.726,
+      "eval_steps_per_second": 1.596,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.0989814733312e+16,
+  "total_flos": 5.738831856027648e+16,
   "trial_name": null,
   "trial_params": null
 }