Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7a2c56811085a8befd160ec89fab677e453207d020e32f82920919cdd0c1e8
+oid sha256:b679e0c75a8643214afae860a6ac9005a9f9a75a2f2f5c537c9e222964481a43
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98defc4369dc5ed5ef6150d824ec69a16d9c8bcff9d62719b0bfcf76183bfb91
+oid sha256:c72c670e793ff2c7d8d8e295289dbdf4f7506db32a0c57072c1daae89d0c0167
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f421960082621eb5d18a65ca61753285f8400dd4a46495b865c4b2f5f1806c
+oid sha256:78e602e0905f2f4cd3eaf79c0118d57897fc5559f4a434cf3e4f71108013ea94
 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": 1.102936029434204,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.0996404886245728,
+  "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": 10.338,
       "eval_steps_per_second": 1.296,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 0.9517,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.0996404886245728,
+      "eval_runtime": 186.5382,
+      "eval_samples_per_second": 10.346,
+      "eval_steps_per_second": 1.297,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.130969014206382e+17,
+  "total_flos": 1.2719281132194202e+17,
   "trial_name": null,
   "trial_params": null
 }