Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d33f338e1e9c39928855dff98bd185864db17a9257e3e67b608d3c2983b9c7b
+oid sha256:9168945734e861efc761211602678943bfc5e627e3517e9b3caf8d680a27a178
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8034e399f236dac3e043878eb1d9b1537f45ffbb6d0bdb9c7067553d54818250
+oid sha256:8071c27882b324455d8c2a198a5170e418362ab74b93b4e8dc214147065d0877
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2d8633c0aa6b6a8b67d82ed27db4d43d78e0131786fdb9f59325ae79b03026
+oid sha256:ea2cea2431b2cb13f64c00a95b19e0f4020d70871d487340ebce67c5fed0ac3a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2813292741775513,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.6666666666666665,
+  "best_metric": 1.2773118019104004,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.8,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 12.886,
       "eval_steps_per_second": 1.616,
       "step": 2000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002,
+      "loss": 1.0479,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 1.2773118019104004,
+      "eval_runtime": 112.6322,
+      "eval_samples_per_second": 12.883,
+      "eval_steps_per_second": 1.616,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2725057626251264e+17,
+  "total_flos": 1.3360108283633664e+17,
   "trial_name": null,
   "trial_params": null
 }