Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:517efa484050f72bed1546fbdd48ff728b3c93cf9f0bd63f7f974ced8b61d3de
+oid sha256:988267fa91dde76c97d5f9f4bdc827ce21f64d3d8210cfb9e0a95599c6b2e344
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6512cd6da4790ab42a6558686fdeeeb8581235e8e45aeaa0cf034b06a162e721
+oid sha256:6186822b08fc70083736d46e84b3aec159961ab50fedc26342e3b2afb0c7d175
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40d056dfa1777aca34129d3102c8e171e32b1af83bd9f7998bbdc382182dd6c8
+oid sha256:005f9e7198481e74b4ed4ba5af793791c506ea467a1d762ec7bb45828f94cc44
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46e34bd832d1dff745713c9d798d0727e0b8a7bdb54c1fe6616fdc922fb8eebf
+oid sha256:3d4bbd98ecf2ab541efa2298ba67df8340fabd983f46354f188b96f0ce56b64f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 3609,
+  "global_step": 4812,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -80,6 +80,28 @@
       "eval_samples_per_second": 14.053,
       "eval_steps_per_second": 1.764,
       "step": 3609
+    },
+    {
+      "epoch": 3.3250207813798838,
+      "grad_norm": 54536.17578125,
+      "learning_rate": 6.699916874480467e-06,
+      "loss": 0.3517,
+      "step": 4000
+    },
+    {
+      "epoch": 3.7406483790523692,
+      "grad_norm": 41206.8203125,
+      "learning_rate": 5.037406483790524e-06,
+      "loss": 0.3409,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.29912063479423523,
+      "eval_runtime": 35.2976,
+      "eval_samples_per_second": 13.995,
+      "eval_steps_per_second": 1.756,
+      "step": 4812
     }
   ],
   "logging_steps": 500,
@@ -99,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.758000534257664e+16,
+  "total_flos": 2.344000712343552e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null