Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f80aa8ccea89cb639b343d2ad8580715f157b72d00aa20168dddf65d0e7719f
+oid sha256:c871537e60075bfb3489556aafd3189cb389d9f771c3b038cd68d18648dc4c51
 size 1447317080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aadfde956bfba1a41c94a0e2a8d5c29c93edc8739d0b00174c1f5b9881b86dd
+oid sha256:e17967af6c6a6182fc9f28b28fae49dc7777a8262ac32bfd5cdffad338f53734
 size 2894813242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0310085a91ffe31e52ed785525e1b1bbd8d02ab8f4fd9ae7f554a009347d00a0
+oid sha256:f851f9fcf8f9fad3c79a18ff4e2f6430c43dce0659f5f180b8393cafa847ebe7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4036673307418823,
-  "best_model_checkpoint": "./opt_trained2/checkpoint-803",
-  "epoch": 1.0,
+  "best_metric": 0.3986678719520569,
+  "best_model_checkpoint": "./opt_trained2/checkpoint-1606",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 803,
+  "global_step": 1606,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,28 @@
       "eval_samples_per_second": 10.436,
       "eval_steps_per_second": 2.609,
       "step": 803
+    },
+    {
+      "epoch": 1.2453300124533002,
+      "grad_norm": 1.277639627456665,
+      "learning_rate": 0.0003751183063511831,
+      "loss": 3.2109,
+      "step": 1000
+    },
+    {
+      "epoch": 1.86799501867995,
+      "grad_norm": 1.1930288076400757,
+      "learning_rate": 0.00036273972602739727,
+      "loss": 3.4898,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3986678719520569,
+      "eval_runtime": 273.4619,
+      "eval_samples_per_second": 10.444,
+      "eval_steps_per_second": 2.611,
+      "step": 1606
     }
   ],
   "logging_steps": 500,
@@ -41,7 +63,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.128721416568e+16,
+  "total_flos": 6.257442833136e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null