Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d4e8c77d932ef7921f68a2e3dd2d2cfe32e688986f187d0e4faa9c1595c7c92
+oid sha256:517efa484050f72bed1546fbdd48ff728b3c93cf9f0bd63f7f974ced8b61d3de
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d05f8746492cd01939e615ae8172b6766dec48f8b0c883dac9c17d57f13a0db
+oid sha256:6512cd6da4790ab42a6558686fdeeeb8581235e8e45aeaa0cf034b06a162e721
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09113c16371e6a869eef77b49617636a63431cd060eb4249f80d76152979a997
+oid sha256:40d056dfa1777aca34129d3102c8e171e32b1af83bd9f7998bbdc382182dd6c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b396ae3042221eef0dc97ca0923b4df3aecf5997b18c176a31be2b398fa5a4b2
+oid sha256:46e34bd832d1dff745713c9d798d0727e0b8a7bdb54c1fe6616fdc922fb8eebf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 2406,
+  "global_step": 3609,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,35 @@
       "eval_samples_per_second": 14.001,
       "eval_steps_per_second": 1.757,
       "step": 2406
+    },
+    {
+      "epoch": 2.0781379883624274,
+      "grad_norm": 33540.33203125,
+      "learning_rate": 1.1687448046550292e-05,
+      "loss": 0.3783,
+      "step": 2500
+    },
+    {
+      "epoch": 2.493765586034913,
+      "grad_norm": 42853.05078125,
+      "learning_rate": 1.002493765586035e-05,
+      "loss": 0.3694,
+      "step": 3000
+    },
+    {
+      "epoch": 2.9093931837073983,
+      "grad_norm": 26482.623046875,
+      "learning_rate": 8.362427265170407e-06,
+      "loss": 0.3572,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.3047104477882385,
+      "eval_runtime": 35.153,
+      "eval_samples_per_second": 14.053,
+      "eval_steps_per_second": 1.764,
+      "step": 3609
     }
   ],
   "logging_steps": 500,
@@ -70,7 +99,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.172000356171776e+16,
+  "total_flos": 1.758000534257664e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null