Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180799923d60094382644c54290e59e477207941e6639fc451e41236d3e1eb4a
+oid sha256:622ceda914025a3cb6c3aea861afbd414ca14e4ada07549a490403bb60ed436e
 size 1447317080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d29276ef613a478783a8b31a7b2c7f90cd8b1790f90084070a56b470439ccc13
+oid sha256:3e7ab6da7bbcf285ba92b6a319955403be98c63cb8e5f808e2fac2b858c00b04
 size 2894813242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e1a0159d4af8f2aff362ffe79d7838d580f34554f42bcc8b39206c91c36519
+oid sha256:230edc29c7f4d0d371abd36f9f7bae2a11f65b418f970748364cb37008e3f3ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3892712891101837,
-  "best_model_checkpoint": "./opt_trained2/checkpoint-2409",
-  "epoch": 3.0,
+  "best_metric": 0.37884894013404846,
+  "best_model_checkpoint": "./opt_trained2/checkpoint-3212",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 2409,
+  "global_step": 3212,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 10.439,
       "eval_steps_per_second": 2.61,
       "step": 2409
+    },
+    {
+      "epoch": 3.1133250311332503,
+      "grad_norm": 0.4317278563976288,
+      "learning_rate": 0.0003378331257783313,
+      "loss": 3.0505,
+      "step": 2500
+    },
+    {
+      "epoch": 3.7359900373599,
+      "grad_norm": 0.3730609118938446,
+      "learning_rate": 0.00032537982565379825,
+      "loss": 2.9785,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.37884894013404846,
+      "eval_runtime": 273.844,
+      "eval_samples_per_second": 10.429,
+      "eval_steps_per_second": 2.607,
+      "step": 3212
     }
   ],
   "logging_steps": 500,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.386164249704e+16,
+  "total_flos": 1.2514885666272e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null