Training in progress, step 21000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c86189a77f037cbdd789ce6756a983f35d8424562557bec70f1d6f9478782956
+oid sha256:3b28df1971539671747e3a778afbdb5f38bcc6ab00d7766a5153b19f29b78c8d
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f3b9b0a558aef18a5c43688fb84bceaf30915a8e0f42a94e913404b25ec6988
+oid sha256:7061f248e70b39002a88a3f1e8979a8a5203e1f6c7433a05e47b1416a56cf81d
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1cb24b28fd79d1b2e08e97a1214134b31144058db4370cb477a455701ee578a
+oid sha256:57271955ed47e1769456cbc5629f14409b6b61904f3f76f733b63102e083bba0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d6f63efc0f911cd45ec87b983b2cf047da0e86188af05e21eda256bea09b7e
+oid sha256:cd63ac70e4657463d9ad6dfb25e72c667be965cdfce9d42626f1f00c9c329b89
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3666666666666667,
+  "epoch": 1.4,
   "eval_steps": 500,
-  "global_step": 20500,
+  "global_step": 21000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1450,6 +1450,41 @@
       "learning_rate": 1.0891555555555557e-05,
       "loss": 0.0609,
       "step": 20500
+    },
+    {
+      "epoch": 1.3733333333333333,
+      "grad_norm": 0.21939997375011444,
+      "learning_rate": 1.0847111111111112e-05,
+      "loss": 0.0612,
+      "step": 20600
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.23522862792015076,
+      "learning_rate": 1.0802666666666667e-05,
+      "loss": 0.0555,
+      "step": 20700
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 0.1318577080965042,
+      "learning_rate": 1.0758222222222223e-05,
+      "loss": 0.0608,
+      "step": 20800
+    },
+    {
+      "epoch": 1.3933333333333333,
+      "grad_norm": 0.11281125992536545,
+      "learning_rate": 1.0714222222222224e-05,
+      "loss": 0.0579,
+      "step": 20900
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.15145792067050934,
+      "learning_rate": 1.066977777777778e-05,
+      "loss": 0.0567,
+      "step": 21000
     }
   ],
   "logging_steps": 100,
@@ -1469,7 +1504,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.993454702592e+16,
+  "total_flos": 5.115246280704e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null