Training in progress, step 1600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006d5423774ce147556916feb4880c2a318e2db246b2b2aae77c70c262b87d8c
+oid sha256:84ec469b9a931ceaa48172563637e8990933d25e1be502af4e7ae5611becf20f
 size 498637432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed5fef826622fde30d58ac515519a35fe622e1ff9c330c44e5ff679cdbf85a4e
+oid sha256:2cc9c3001940abe627d7be7b80893c4009a4964ba4991d59443c18eb73cc1fdc
 size 997397434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f710071ace95ee6fb0d119c8c399725a15bad03bd29089ff217afd98a60e0c
+oid sha256:797f580e891f5abde287b12800586d04473118777fd6947254183148e618fd1b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:166c304947f6ea4694d3341b4f5eb9a0bfc5f70599e010ae3ddac01e2128315e
+oid sha256:effa0a4f47489c26c9eb6d82a01e44c96441806dcdd44004dc1934ba079fa6b3
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67f5472fb54cc4433f9ce9050bf948f55c4acdc5a9507e5c551d62f0cbc86596
+oid sha256:24314368a361a98a57954473631fda87453de83e38555b1dca4f24bf2f32a584
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 800,
   "best_metric": 0.8289822527097279,
   "best_model_checkpoint": "roberta_en_med_merged_classes/checkpoint-800",
-  "epoch": 23.334728033472803,
+  "epoch": 26.669456066945607,
   "eval_steps": 200,
-  "global_step": 1400,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -183,6 +183,31 @@
       "eval_samples_per_second": 908.215,
       "eval_steps_per_second": 28.453,
       "step": 1400
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 4.346404075622559,
+      "learning_rate": 1.2969135802469138e-05,
+      "loss": 0.1226,
+      "step": 1500
+    },
+    {
+      "epoch": 26.669456066945607,
+      "grad_norm": 4.3527913093566895,
+      "learning_rate": 1.2351851851851852e-05,
+      "loss": 0.1116,
+      "step": 1600
+    },
+    {
+      "epoch": 26.669456066945607,
+      "eval_accuracy": 0.8452127166558532,
+      "eval_f1_macro": 0.8271054182389765,
+      "eval_f1_weighted": 0.8453577277246404,
+      "eval_loss": 0.6010852456092834,
+      "eval_runtime": 11.9133,
+      "eval_samples_per_second": 905.627,
+      "eval_steps_per_second": 28.372,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -202,7 +227,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.7537119387182285e+17,
+  "total_flos": 4.29018655215231e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null