Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2e55a44aaf92d249e31e206ac08ef973e30c7697ad6a53ce491eef5a74cea3b
+oid sha256:fbe686a29014652850a0b3c527fbca499406bd1d5299925be3de3c5bd653523b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc777f2ba4eb3b89cf776190c8b4e7d168e24c585aa3711238ee471d3aa9745
+oid sha256:e454caabc6b9a8add8ae75f29a8fb620ebcd90904c1d1ba7bf71f4e471856877
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8b98e2024de40ef400abf18ba3f39e1a6407c6f5496016292c9acbf052f0dd
+oid sha256:fb7e70944ee032b710f184512939412d316802644141141a5b9b23e848841cc1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4181303977966309,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 1.407381296157837,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 1.7333333333333334,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 15.575,
       "eval_steps_per_second": 1.954,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 1.1844,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 1.407381296157837,
+      "eval_runtime": 94.8759,
+      "eval_samples_per_second": 15.294,
+      "eval_steps_per_second": 1.918,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.01220463147008e+16,
+  "total_flos": 7.595995991076864e+16,
   "trial_name": null,
   "trial_params": null
 }