Training in progress, step 2100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456747f9f9062a632d390b887bd07bf9bdbb14149eb73c1f8e4653a9965e56be
+oid sha256:cd05797eba4af2ca90d5c8aedc8a2a141b146602a03127e89e52aeaa78c51cb0
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f671c6c5c8494b3e46c55e252556e8340775a3483a44f7743c6b1f9d39f546d
+oid sha256:5505d7094552ed7661bfc40965c065158aa0046fb8d6f07d161f457d37e1da5f
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145ba2f9dd4ec81afed9af18b40011a6f60a67d579bb7dbd4684df15787bd991
+oid sha256:51d51837dd781f74c987a30a788fb34245746bf69bd7d3e79d3c65a22612eb23
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b383e59a1ebdc9bcae3e7149a6bf24375cdea86f20952bcbd60b95e565536d7
+oid sha256:1cfd5e7fe0683153dd34505da9c613acbbf24ffe8ad301d2cfe6618d63d98896
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e8e833d541e6dd46d7f1e61b855496a085cf2d11854131ccb1e25d44309925
+oid sha256:cfc574ffdad315f35625e325f3592a5576c7dfb0a7edc69111f4fc7430d5f8bd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb26b1e8203066db35c249e162eec7503528d6c26174477aeef1a623dbe86327
+oid sha256:207a31c0d5216576c258e1e019adc0b0471874547e0afd1e435ea0357317731f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8b566dcf926fa2676b4cb6372c85569269920704cd9ac2594aad37fba636c71
+oid sha256:62f7b847089c23254653d5114a76b90d4e846cc6929c539b8969df05d9501e6f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8446890115737915,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1900",
-  "epoch": 2.677376171352075,
+  "best_metric": 0.8368203639984131,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2100",
+  "epoch": 2.8112449799196786,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,6 +307,21 @@
       "eval_samples_per_second": 890.609,
       "eval_steps_per_second": 3.599,
       "step": 2000
+    },
+    {
+      "epoch": 2.8112449799196786,
+      "grad_norm": 0.2042614370584488,
+      "learning_rate": 0.000718875502008032,
+      "loss": 0.8372,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8112449799196786,
+      "eval_loss": 0.8368203639984131,
+      "eval_runtime": 6.3674,
+      "eval_samples_per_second": 893.931,
+      "eval_steps_per_second": 3.612,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -321,7 +336,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -335,7 +350,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.262454153216e+16,
+  "total_flos": 7.6255768608768e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null