Training in progress, step 27000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d79b372779eff7f0c6aceb504965064dd1c783ad82104b4d76980d00e49918c
+oid sha256:5aee5c58e4fc85927dc4013d0fe750e56e604920994d516f324190a1a8d7a05f
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c628badd7736af0b2faf987d91b45461eb187ce865defe1587b4f0f12761f4a
+oid sha256:d58926cc53cc96e7baec8d580220f0a290e47d6bc25d45f7fd7e61bf35d05d9a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca75d61d47f3eab98fc406af0fc3456adbe0767939034d58dea95e5d6ff029b5
+oid sha256:8469fa4abc9740f9af7a5dacb10ea8c5107fb6c8cbc91f6fcad8c8b05132d7d0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82350f62694be97e6ec7d5caa84c96c6ffb8c480e6a50519ae958022a2c0417
+oid sha256:8dc2ab4847205143252d3ebb3c6929a744853487e6aadfb5f1c78d5dcdea141c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7666666666666666,
+  "epoch": 1.8,
   "eval_steps": 500,
-  "global_step": 26500,
+  "global_step": 27000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1870,6 +1870,41 @@
       "learning_rate": 8.226222222222224e-06,
       "loss": 0.0541,
       "step": 26500
+    },
+    {
+      "epoch": 1.7733333333333334,
+      "grad_norm": 0.3220883309841156,
+      "learning_rate": 8.181777777777779e-06,
+      "loss": 0.0543,
+      "step": 26600
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.18442386388778687,
+      "learning_rate": 8.137333333333334e-06,
+      "loss": 0.0633,
+      "step": 26700
+    },
+    {
+      "epoch": 1.7866666666666666,
+      "grad_norm": 0.25864550471305847,
+      "learning_rate": 8.09288888888889e-06,
+      "loss": 0.0572,
+      "step": 26800
+    },
+    {
+      "epoch": 1.7933333333333334,
+      "grad_norm": 0.23834674060344696,
+      "learning_rate": 8.048444444444445e-06,
+      "loss": 0.0537,
+      "step": 26900
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.1399671733379364,
+      "learning_rate": 8.004e-06,
+      "loss": 0.0572,
+      "step": 27000
     }
   ],
   "logging_steps": 100,
@@ -1889,7 +1924,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.454953639936e+16,
+  "total_flos": 6.576745218048e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null