Training in progress, step 8200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a38420795d5d0d50e960f49d06adbc5c6bdd8169cb909db6fc15ce6766e6ef0e
+oid sha256:783309b92bf904a4987195d65f9c3e49a0a7df8a83abb12055e5dba735e35ba3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8275e665b6929f18028bebc898bdfbc6c0a222deb0f41fb9bf83f931ffb4e789
+oid sha256:c2c0aba8b4efcec01add15ebdb21629b6fb824568690d50ff04fee5ba95bce6f
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c603634c267f29bf2d121dbeedb38074ba961e12d7046289f8ab33d4f4a419be
+oid sha256:a6e69560bad23a6fb4e8cc5cd668902a0c825d77164f5297a8878eeef71f6dbf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78825347619efcca6295a2a1e8c4e9f6bdf3806b28ce14630667667fc69bc6a0
+oid sha256:612d436028557394444e8286b0ca62afad5efea9ac857621a2bc4c96f8a94c3b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005949304489122068,
+  "epoch": 0.00609803710135012,
   "eval_steps": 2000,
-  "global_step": 8000,
+  "global_step": 8200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,13 @@
       "learning_rate": 1.9999930326577432e-05,
       "loss": 1.5593,
       "step": 8000
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.441413640975952,
+      "learning_rate": 1.999992679444808e-05,
+      "loss": 1.5118,
+      "step": 8200
     }
   ],
   "logging_steps": 200,
@@ -294,7 +301,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.0490681947287552e+17,
+  "total_flos": 1.0738682585918669e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null