Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e0029d69f2e02a51eb9d5db1c6eb0204c4e33d683b908a1f2fdd1cedde3b0d
+oid sha256:bacfee4e852aafb2738a24d09e5c4af4b855c4c32fb37fce5da9f9cb5341d284
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eef27d086e7c06aa1c79b9cde0fc0f2c8ff7293d1a6ed6f4b9a9a785d7cb781
+oid sha256:b011bd7927b529702f85b6fa8233ee827404eef6364a84445c4e312223498d94
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a7adea43dcf6387b396d924985ba3d8d2ca0009f0291528a1342a56d78b48c
+oid sha256:ab69399c8eb447c951d8e52fcc1c52406938e7f812da28a8e362df21f802f42a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3928134441375732,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.6666666666666666,
+  "best_metric": 1.379417896270752,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.8,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 12.724,
       "eval_steps_per_second": 1.595,
       "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 1.1421,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.379417896270752,
+      "eval_runtime": 151.6496,
+      "eval_samples_per_second": 12.727,
+      "eval_steps_per_second": 1.596,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.186631141392384e+16,
+  "total_flos": 3.823579745427456e+16,
   "trial_name": null,
   "trial_params": null
 }