Training in progress, step 1100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0cb17255184785b2ba3df5819549de3498e4d0e7f5e4a2729e64f86ed29de26
+oid sha256:74cad29765d7eeaf0798dfe99d70605b73505b56db5675476deac5bce8b2bd92
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cb07b7152ff3d568067d45b91b044799060a8b3ac1266a4369878feec01534
+oid sha256:e7e5414ede6ff97d0f574e34a66d664c6e2b33fda48d31eb59891c58fa9e5571
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e42ef0c0957b2a7ec805704d6efb2633584722c7af0bcea1764796bb5bf281
+oid sha256:298dca4ef3ed6fb66ee994903dbf37725d0d0ecea6edef108d1e34863545fc10
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db89a18915ddabc34d8708a039b979f64d5e4cc545f23f1fce000552d7bc042d
+oid sha256:39935e7b6aa26b9c30d9a05991f0711d238602e35f3dc320984bdc087ec43877
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bae1cf896f870000f671d939a3f1578d4d9fe08093081f10392f661f08c70d15
+oid sha256:2429e043941b88180a7f42eb58397a6fabb9176cccf0404d3714e1cc142d0838
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af89e3e6ffd392e6a4fda5011e523226c849189f0277976c34d1b371ff1023d
+oid sha256:e7fba82a6aeef46864a8c5c8c25e48b11e02dd297752e8eaeeef1f62c51b062d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4405150630b4301b5298e1c0d4cb42b626ca737cad764049dcb8e7d48dbfef79
+oid sha256:3fc1e1bf421f50dc04c51b86d69cc292444452defdf9f3ea4559b9ad288a68b3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9004408717155457,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1000",
-  "epoch": 1.3386880856760375,
+  "best_metric": 0.8951759934425354,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1100",
+  "epoch": 1.4725568942436413,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,6 +157,21 @@
       "eval_samples_per_second": 891.467,
       "eval_steps_per_second": 3.602,
       "step": 1000
+    },
+    {
+      "epoch": 1.4725568942436413,
+      "grad_norm": 0.2045995146036148,
+      "learning_rate": 0.0008527443105756359,
+      "loss": 0.9242,
+      "step": 1100
+    },
+    {
+      "epoch": 1.4725568942436413,
+      "eval_loss": 0.8951759934425354,
+      "eval_runtime": 6.39,
+      "eval_samples_per_second": 890.768,
+      "eval_steps_per_second": 3.599,
+      "step": 1100
     }
   ],
   "logging_steps": 100,
@@ -185,7 +200,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.631227076608e+16,
+  "total_flos": 3.9943497842688e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null