Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b76cd3dd8f3af0bdc418b56e3cffdf73e51cdc2486e299e0e3037780b470dad2
+oid sha256:6b338b089c0a19c748ec05a0a751eff19711f1f40ae9ef4268c37844a5eafb48
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d0560b2a56e05543f23bf5dc0ad584db7470790d75684eb4f29c73dea8532c6
+oid sha256:b4551f71a61db260fb246efc25326387b7e9fe6eaa0d4bd529abd3b2f0617020
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d764b7a99b8ed179d4df939f9536e72a7d94978db9a5c37328a6aaf12f5c3e
+oid sha256:46f4b8978ebc50af66f13b17f908e2b5f60d1f770cdef24a28bf8108b6b3b4ac
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3962c21f6062f8f3c755e0be0db565d65f484e53aa2e30812e9a1dd0cde7e4
+oid sha256:8cad5f03d51098deec16f832dd35e17c987b9fec698c0d54d55ec05fc16c3cfe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2978520393371582,
-  "best_model_checkpoint": "./opt_trained/checkpoint-1288",
-  "epoch": 4.0,
+  "best_metric": 0.29741692543029785,
+  "best_model_checkpoint": "./opt_trained/checkpoint-1610",
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 1288,
+  "global_step": 1610,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -53,6 +53,21 @@
       "eval_samples_per_second": 19.644,
       "eval_steps_per_second": 4.911,
       "step": 1288
+    },
+    {
+      "epoch": 4.659922178988327,
+      "grad_norm": 2.5350475311279297,
+      "learning_rate": 3.484979197425745e-05,
+      "loss": 0.2948,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.29741692543029785,
+      "eval_runtime": 145.627,
+      "eval_samples_per_second": 19.612,
+      "eval_steps_per_second": 4.903,
+      "step": 1610
     }
   ],
   "logging_steps": 500,
@@ -72,7 +87,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.371119009792e+16,
+  "total_flos": 6.71389876224e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null