Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eeef6ea82868fed037096afaae75138d366fdd8a948a478a6d39da41c0320cc
+oid sha256:91fd7fef7c913bb40166ed36edd2f41fccb334c604d8ad710dd729958231a38c
 size 1447317080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e307af0d3d8da03f1b9c643b876554b892185b2c269d203e47abe5885b91daa
+oid sha256:e44bc94aa5951947f3a443e56090b2942fbbc3833f1851ba62e08e0d0b08ab9b
 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 sha256:3f9b5be710a7d11d99443218152501810ac7e04613867545dd1469d3cfd97c06
+oid sha256:8e5a8207eb085bcd0143e42fa68c8c3ba984241f8e091d2d1b847c4f98e5ec17
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.344450980424881,
   "best_model_checkpoint": "./opt_trained2/checkpoint-803",
-  "epoch": 1.0,
+  "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": 10.457,
       "eval_steps_per_second": 2.614,
       "step": 803
+    },
+    {
+      "epoch": 1.2453300124533002,
+      "grad_norm": 1.1673122644424438,
+      "learning_rate": 0.000375093399750934,
+      "loss": 2.6965,
+      "step": 1000
+    },
+    {
+      "epoch": 1.86799501867995,
+      "grad_norm": 0.7170485258102417,
+      "learning_rate": 0.000362640099626401,
+      "loss": 2.5469,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3459263741970062,
+      "eval_runtime": 272.8846,
+      "eval_samples_per_second": 10.466,
+      "eval_steps_per_second": 2.616,
+      "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