Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7c7b067ce43a0be0be0f92ea01066fe8ed60f6f5f80359ee347257fbaa14a6
+oid sha256:1801d110451c0363b6c96a6beb709896d1e97932e109f064917b003009fc7531
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a76102b6fc4e10f811ee1edf543de76c09456828bc9f6d9f8e1b936ec810e71
+oid sha256:dad47e1bd71fe5d6ce8ab2ddc71e1f433caf30cc0edbeaa8bee27bcbcb73645c
 size 2423802

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b91ead1bc4475814472ed6c199136a17cbef66ddbeed94488d3061d1183ec5d
+oid sha256:bd42e404833ad689f8f0afea3e690a640621e31bc600a66bf369e5fbdf9e45d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d73ec88250c78a08053b936383d3830db79e459629e27383da2e03ffab044694
+oid sha256:092d025c9fcbd51424bdca7f48bfd52fefca1fab60b5376be0369f85dfec9dd1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0002957359544877931,
+  "epoch": 0.00031130100472399273,
   "eval_steps": 500,
-  "global_step": 380,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -140,6 +140,13 @@
       "learning_rate": 4.999181729716214e-05,
       "loss": 2.6197,
       "step": 380
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.073474407196045,
+      "learning_rate": 4.998715010818479e-05,
+      "loss": 2.6627,
+      "step": 400
     }
   ],
   "logging_steps": 20,
@@ -147,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1740689046355968.0,
+  "total_flos": 1824387808739328.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null