Training in progress, epoch 16, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66200acd6c20b3e5f776dd34d1dce04a462cff382acb5ae4670ee560518aaaf9
+oid sha256:85a37ab425a5bb455eb5138be42e451b4f6504a4ec63d8c4323c617cb3ebc33e
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d55fa5ee514060d7787608dec3a888a028a7841ddb0bd524977d24948976b24e
+oid sha256:fb0e7b73e702883e0aea72dd82fc77ae713a9e1e0ea8fae495ef88376c79291d
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc091a107ead0fd888fc4fea93ea268674953a0350c819218e401bfc73856e7d
+oid sha256:d2f665ad4a75c89f6711748909d7b7bdbe353d41461e39d9efde1e7c8c122662
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89399495261c74d8cccbea129b463394fdf91e1c31568f5b62fa945b79a3648c
+oid sha256:8db07ed3922379a7896753ff18d75baed592f87392b70da4afc38e708f68e8df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.997999636297509,
+  "epoch": 16.997999636297507,
   "eval_steps": 50,
-  "global_step": 5488,
+  "global_step": 5831,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1642,6 +1642,111 @@
       "eval_samples_per_second": 41.5,
       "eval_steps_per_second": 20.75,
       "step": 5450
+    },
+    {
+      "epoch": 16.03491543917076,
+      "grad_norm": 56.59613037109375,
+      "learning_rate": 1.9825072886297377e-05,
+      "loss": 0.7036,
+      "step": 5500
+    },
+    {
+      "epoch": 16.03491543917076,
+      "eval_loss": 0.6698302626609802,
+      "eval_runtime": 118.2947,
+      "eval_samples_per_second": 40.796,
+      "eval_steps_per_second": 20.398,
+      "step": 5500
+    },
+    {
+      "epoch": 16.180396435715586,
+      "grad_norm": 105.1061019897461,
+      "learning_rate": 1.9096209912536444e-05,
+      "loss": 0.6882,
+      "step": 5550
+    },
+    {
+      "epoch": 16.180396435715586,
+      "eval_loss": 0.6712303161621094,
+      "eval_runtime": 116.6934,
+      "eval_samples_per_second": 41.356,
+      "eval_steps_per_second": 20.678,
+      "step": 5550
+    },
+    {
+      "epoch": 16.325877432260413,
+      "grad_norm": 48.417171478271484,
+      "learning_rate": 1.836734693877551e-05,
+      "loss": 0.6877,
+      "step": 5600
+    },
+    {
+      "epoch": 16.325877432260413,
+      "eval_loss": 0.6700485944747925,
+      "eval_runtime": 117.069,
+      "eval_samples_per_second": 41.224,
+      "eval_steps_per_second": 20.612,
+      "step": 5600
+    },
+    {
+      "epoch": 16.47135842880524,
+      "grad_norm": 71.32566833496094,
+      "learning_rate": 1.7638483965014578e-05,
+      "loss": 0.6912,
+      "step": 5650
+    },
+    {
+      "epoch": 16.47135842880524,
+      "eval_loss": 0.6679624915122986,
+      "eval_runtime": 116.8492,
+      "eval_samples_per_second": 41.301,
+      "eval_steps_per_second": 20.651,
+      "step": 5650
+    },
+    {
+      "epoch": 16.616839425350065,
+      "grad_norm": 50.87607955932617,
+      "learning_rate": 1.6909620991253645e-05,
+      "loss": 0.6874,
+      "step": 5700
+    },
+    {
+      "epoch": 16.616839425350065,
+      "eval_loss": 0.6632840633392334,
+      "eval_runtime": 116.778,
+      "eval_samples_per_second": 41.326,
+      "eval_steps_per_second": 20.663,
+      "step": 5700
+    },
+    {
+      "epoch": 16.76232042189489,
+      "grad_norm": 62.6202392578125,
+      "learning_rate": 1.6180758017492712e-05,
+      "loss": 0.685,
+      "step": 5750
+    },
+    {
+      "epoch": 16.76232042189489,
+      "eval_loss": 0.6643268465995789,
+      "eval_runtime": 116.7182,
+      "eval_samples_per_second": 41.347,
+      "eval_steps_per_second": 20.674,
+      "step": 5750
+    },
+    {
+      "epoch": 16.907801418439718,
+      "grad_norm": 57.434730529785156,
+      "learning_rate": 1.545189504373178e-05,
+      "loss": 0.6861,
+      "step": 5800
+    },
+    {
+      "epoch": 16.907801418439718,
+      "eval_loss": 0.663483738899231,
+      "eval_runtime": 116.4065,
+      "eval_samples_per_second": 41.458,
+      "eval_steps_per_second": 20.729,
+      "step": 5800
     }
   ],
   "logging_steps": 50,
@@ -1661,7 +1766,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.42943403473109e+18,
+  "total_flos": 1.5187665302784573e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null