Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d87e5dad3c6690fef034be4bc57caa0fc8ab42dcb5723e4b9adc81d538f3bf5
+oid sha256:7d4e8c77d932ef7921f68a2e3dd2d2cfe32e688986f187d0e4faa9c1595c7c92
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a071225e50f1f2115f0d6b0cbd73237ff385d17d8c27011fa558ff27daccd30c
+oid sha256:1d05f8746492cd01939e615ae8172b6766dec48f8b0c883dac9c17d57f13a0db
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d390f0bc19e72100cddb4d23fc68a96cec6d307bdf7ac46025c4464ebb3220c
+oid sha256:09113c16371e6a869eef77b49617636a63431cd060eb4249f80d76152979a997
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d0a449f7b5d61be4b5aa6ee26ed2ca700da9efe3681ef85b70cf229dedfd35e
+oid sha256:b396ae3042221eef0dc97ca0923b4df3aecf5997b18c176a31be2b398fa5a4b2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 1203,
+  "global_step": 2406,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -29,6 +29,28 @@
       "eval_samples_per_second": 14.075,
       "eval_steps_per_second": 1.767,
       "step": 1203
+    },
+    {
+      "epoch": 1.2468827930174564,
+      "grad_norm": 34293.8984375,
+      "learning_rate": 1.5012468827930176e-05,
+      "loss": 0.4256,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6625103906899419,
+      "grad_norm": 44778.91015625,
+      "learning_rate": 1.3349958437240233e-05,
+      "loss": 0.3976,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3173050582408905,
+      "eval_runtime": 35.2821,
+      "eval_samples_per_second": 14.001,
+      "eval_steps_per_second": 1.757,
+      "step": 2406
     }
   ],
   "logging_steps": 500,
@@ -48,7 +70,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5860001780858880.0,
+  "total_flos": 1.172000356171776e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null