Training in progress, step 8400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:783309b92bf904a4987195d65f9c3e49a0a7df8a83abb12055e5dba735e35ba3
+oid sha256:68399e5c313a915751634cf5ffae9ace9416e38938d0103a268d1d11dce06274
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2c0aba8b4efcec01add15ebdb21629b6fb824568690d50ff04fee5ba95bce6f
+oid sha256:4548ac75442441bb1d5da3687ffb1363df171933d0e50d8f215a23de567a8a6b
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6e69560bad23a6fb4e8cc5cd668902a0c825d77164f5297a8878eeef71f6dbf
+oid sha256:d48374e1e6b1447bbeee1d70f64941ccb28e15e76b5206f65f89b25b037eb922
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612d436028557394444e8286b0ca62afad5efea9ac857621a2bc4c96f8a94c3b
+oid sha256:877cbfb7de479f62248634d105d7b3cf3fb2397e07f0e8b78265a455155762d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00609803710135012,
+  "epoch": 0.006246769713578172,
   "eval_steps": 2000,
-  "global_step": 8200,
+  "global_step": 8400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -294,6 +294,13 @@
       "learning_rate": 1.999992679444808e-05,
       "loss": 1.5118,
       "step": 8200
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.383536338806152,
+      "learning_rate": 1.9999923174987494e-05,
+      "loss": 1.5533,
+      "step": 8400
     }
   ],
   "logging_steps": 200,
@@ -301,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.0738682585918669e+17,
+  "total_flos": 1.0986977552390554e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null