Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7f192f2d55fa4756368292ed33fce824ff85eca57caf3562d98cd73fc7a8cee
+oid sha256:1e153b3d390df2c32ad3a759163b88c498760bbeb67e6ea3fecf30ede1a3368e
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0f2660e9ee44744f31ce9d189a6c7fcf6a3af4b38ca63f4f2b343d9bac7010f
+oid sha256:773c76d6a8fed4484f620f4ba9e5fb88e2bdac4c00f550e2cf4fd695b322a9d8
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3048c9a83832dc7b124896464922615490e6501c7f82e77ffa4a7fc426c05b2a
+oid sha256:dc12ca99cd9273c6f93af6bd864f87a70adc24940e768a65157943a9509ca801
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b28276512ef152b82ddcfa3ee0b09e8e0d74b7c64fb28532e915209b8120e2d6
+oid sha256:7645bab3f21c7ba05cfecfff899cc9dea46afbf8ac4bc739ca73a82826afeb3c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0106526613235474,
-  "best_model_checkpoint": "./opt_trained/checkpoint-402",
-  "epoch": 2.0,
+  "best_metric": 1.0082063674926758,
+  "best_model_checkpoint": "./opt_trained/checkpoint-603",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 402,
+  "global_step": 603,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,21 @@
       "eval_samples_per_second": 36.929,
       "eval_steps_per_second": 9.232,
       "step": 402
+    },
+    {
+      "epoch": 2.488169364881694,
+      "grad_norm": 1.6413393020629883,
+      "learning_rate": 0.0003501,
+      "loss": 1.0175,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0082063674926758,
+      "eval_runtime": 77.1371,
+      "eval_samples_per_second": 37.025,
+      "eval_steps_per_second": 9.256,
+      "step": 603
     }
   ],
   "logging_steps": 500,
@@ -42,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.353270219264e+16,
+  "total_flos": 2.029905328896e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null