Training in progress, step 4900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcdef8815876651e789e32f5ba829418b53bdbe3939243812f3f736f8d8cdb6c
+oid sha256:dc8014d8748e7dec7645ff75deb0b0111cb9c6f742c7a7131f58eb33ed12b568
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b613bb035d70d3ea5dd71539a712ebf1251f75ba46a6b0c71d40229483d5493f
+oid sha256:8d4e65de4b080779841194dd872c35a94659f1ffa84ba40bc11248589de15c96
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2c2c42416feac893f835e6829ce76ea3a625b1b8b854969739b7a81e0808468
+oid sha256:a692fca563f784c79b46a8c6beefa68d79b0f463147563be54c585f9c5445d8f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc3ea084381e50acdc6e01e417e6afeda08205af73943c00cc06c438f6132d83
+oid sha256:eec5ee53c096507164c256ff5ef50e9e03821f6656636c2034a53c87ba7c15a8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c77695fbb03c4e55a83075b2d20bc6414bf683d62aff481dc8f99e253cab1ba8
+oid sha256:e89826b206d716fd97bcee65bdd2b08f50143c3dda0842ce4e2b37610f5ca831
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fff0592719262f858821de597e03301f84523b5c8ca2137da9d52b7bd85f4eec
+oid sha256:34ae0937c61c26cef62b07d195d6a8702102333baf881f284e333252395994f5
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62653dc6da916bc0c8d89e707516144c0487544be3b708626da1a9bfdb05f8f
+oid sha256:9953327c201352be7b2c37fe2e8c427302b4ebf9dc7742a1697bb30527f231f0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7769716382026672,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4800",
-  "epoch": 6.42570281124498,
+  "best_metric": 0.775974452495575,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4900",
+  "epoch": 6.5595716198125835,
   "eval_steps": 100,
-  "global_step": 4800,
+  "global_step": 4900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -727,6 +727,21 @@
       "eval_samples_per_second": 895.148,
       "eval_steps_per_second": 3.617,
       "step": 4800
+    },
+    {
+      "epoch": 6.5595716198125835,
+      "grad_norm": 0.2040824443101883,
+      "learning_rate": 0.00034404283801874166,
+      "loss": 0.7194,
+      "step": 4900
+    },
+    {
+      "epoch": 6.5595716198125835,
+      "eval_loss": 0.775974452495575,
+      "eval_runtime": 6.415,
+      "eval_samples_per_second": 887.297,
+      "eval_steps_per_second": 3.585,
+      "step": 4900
     }
   ],
   "logging_steps": 100,
@@ -755,7 +770,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.74298899677184e+17,
+  "total_flos": 1.77930126753792e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null