Training in progress, epoch 14, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e47f1cdc6bb30de3a42755c5e856705a84b91db75b58534b95cf4e4f4bf5059
+oid sha256:e19f56a69991588cb05378ec22af5531354d51618ec45fbad1470b122a478388
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12fb571ddaddabec29d8df0695efe3813dca0abe64dc223bcca27d75770eef43
+oid sha256:d70aa541c9d83a3fda726ee09a4073e42bbb9f06c77938a3a47dfd850c4aea4b
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:613d74de19e0fb35eeea5689475f5e1332f3b307a0a9c8eeaa1e3e8d8c5fe1aa
+oid sha256:efabaf885831c104861d60c36c90e19e984eff0917f39feee04c399b9ccb139a
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:962ad854d2adfe879aa22d99e411b4b35f04f8c2df9821494bc2d1fe0b1197ed
+oid sha256:80c2e7e0c05972926e0ae596907bef103bc8973ac4008bedc0435f6468576df4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.997999636297509,
+  "epoch": 14.997999636297509,
   "eval_steps": 50,
-  "global_step": 4802,
+  "global_step": 5145,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1447,6 +1447,96 @@
       "eval_samples_per_second": 41.321,
       "eval_steps_per_second": 20.66,
       "step": 4800
+    },
+    {
+      "epoch": 14.139661756683033,
+      "grad_norm": 49.7451286315918,
+      "learning_rate": 2.9300291545189507e-05,
+      "loss": 0.7159,
+      "step": 4850
+    },
+    {
+      "epoch": 14.139661756683033,
+      "eval_loss": 0.6897387504577637,
+      "eval_runtime": 116.4679,
+      "eval_samples_per_second": 41.436,
+      "eval_steps_per_second": 20.718,
+      "step": 4850
+    },
+    {
+      "epoch": 14.28514275322786,
+      "grad_norm": 43.889793395996094,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.7094,
+      "step": 4900
+    },
+    {
+      "epoch": 14.28514275322786,
+      "eval_loss": 0.690019428730011,
+      "eval_runtime": 116.7069,
+      "eval_samples_per_second": 41.351,
+      "eval_steps_per_second": 20.676,
+      "step": 4900
+    },
+    {
+      "epoch": 14.430623749772685,
+      "grad_norm": 48.33151626586914,
+      "learning_rate": 2.784256559766764e-05,
+      "loss": 0.7059,
+      "step": 4950
+    },
+    {
+      "epoch": 14.430623749772685,
+      "eval_loss": 0.6871985793113708,
+      "eval_runtime": 116.4941,
+      "eval_samples_per_second": 41.427,
+      "eval_steps_per_second": 20.713,
+      "step": 4950
+    },
+    {
+      "epoch": 14.576104746317512,
+      "grad_norm": 53.56142807006836,
+      "learning_rate": 2.7113702623906705e-05,
+      "loss": 0.7124,
+      "step": 5000
+    },
+    {
+      "epoch": 14.576104746317512,
+      "eval_loss": 0.6843300461769104,
+      "eval_runtime": 116.6779,
+      "eval_samples_per_second": 41.362,
+      "eval_steps_per_second": 20.681,
+      "step": 5000
+    },
+    {
+      "epoch": 14.721585742862338,
+      "grad_norm": 46.541114807128906,
+      "learning_rate": 2.6384839650145775e-05,
+      "loss": 0.708,
+      "step": 5050
+    },
+    {
+      "epoch": 14.721585742862338,
+      "eval_loss": 0.683451235294342,
+      "eval_runtime": 116.8285,
+      "eval_samples_per_second": 41.308,
+      "eval_steps_per_second": 20.654,
+      "step": 5050
+    },
+    {
+      "epoch": 14.867066739407164,
+      "grad_norm": 47.15498352050781,
+      "learning_rate": 2.5655976676384842e-05,
+      "loss": 0.7062,
+      "step": 5100
+    },
+    {
+      "epoch": 14.867066739407164,
+      "eval_loss": 0.6834617853164673,
+      "eval_runtime": 116.6798,
+      "eval_samples_per_second": 41.361,
+      "eval_steps_per_second": 20.681,
+      "step": 5100
     }
   ],
   "logging_steps": 50,
@@ -1466,7 +1556,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.250799370400432e+18,
+  "total_flos": 1.3400806487312302e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null