Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46746dcf87cc775ce233e87c76eda1fd70c4c574d313ac62b6441a453c7f4fb7
+oid sha256:69b2ad78c9146c51f0e2d78c6d1ed0e948a192346df25e7d7e872a8c10ab3851
 size 2695611744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd459df35f653850b7bbbacd289f94d6af499cc205c402f113efc0a0c3397f8
+oid sha256:d119aa4c7293a6a4a22a84598c70e2533ab83a971a44d21f76f6d178a3012fc8
 size 26261260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ada9c6a6e42dd9a052cc6c90ea555e554cf2266902dc66003e3529ef94dd9d78
+oid sha256:3ac7ad6975b02cb2fe1ae9b24f6d70c26049c580d43be5a2feb4f3aa6fc1aa47
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d282d44e6a12e9ca82ec6b42e7f212659678f5fe8c9a58e24a30599040d3e5
+oid sha256:c42147d2487e975dcb8b015449194c61c9350b5c1b3a114ecd6e3942d3403969
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.0,
+  "epoch": 9.929233772571987,
   "eval_steps": 10,
-  "global_step": 1161,
+  "global_step": 1280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1631,6 +1631,174 @@
       "eval_samples_per_second": 22.096,
       "eval_steps_per_second": 5.524,
       "step": 1160
+    },
+    {
+      "epoch": 9.070278184480234,
+      "grad_norm": 20.58171844482422,
+      "learning_rate": 8.59375e-06,
+      "loss": 450.0273,
+      "step": 1170
+    },
+    {
+      "epoch": 9.070278184480234,
+      "eval_runtime": 19.4874,
+      "eval_samples_per_second": 22.168,
+      "eval_steps_per_second": 5.542,
+      "step": 1170
+    },
+    {
+      "epoch": 9.14836505612494,
+      "grad_norm": 21.303646087646484,
+      "learning_rate": 7.8125e-06,
+      "loss": 490.2507,
+      "step": 1180
+    },
+    {
+      "epoch": 9.14836505612494,
+      "eval_runtime": 19.5113,
+      "eval_samples_per_second": 22.141,
+      "eval_steps_per_second": 5.535,
+      "step": 1180
+    },
+    {
+      "epoch": 9.226451927769643,
+      "grad_norm": 21.960155487060547,
+      "learning_rate": 7.031250000000001e-06,
+      "loss": 467.3604,
+      "step": 1190
+    },
+    {
+      "epoch": 9.226451927769643,
+      "eval_runtime": 19.5396,
+      "eval_samples_per_second": 22.109,
+      "eval_steps_per_second": 5.527,
+      "step": 1190
+    },
+    {
+      "epoch": 9.304538799414349,
+      "grad_norm": 20.90469741821289,
+      "learning_rate": 6.25e-06,
+      "loss": 471.1743,
+      "step": 1200
+    },
+    {
+      "epoch": 9.304538799414349,
+      "eval_runtime": 19.551,
+      "eval_samples_per_second": 22.096,
+      "eval_steps_per_second": 5.524,
+      "step": 1200
+    },
+    {
+      "epoch": 9.382625671059053,
+      "grad_norm": 20.1269588470459,
+      "learning_rate": 5.46875e-06,
+      "loss": 472.9441,
+      "step": 1210
+    },
+    {
+      "epoch": 9.382625671059053,
+      "eval_runtime": 19.5496,
+      "eval_samples_per_second": 22.098,
+      "eval_steps_per_second": 5.524,
+      "step": 1210
+    },
+    {
+      "epoch": 9.460712542703758,
+      "grad_norm": 22.04480743408203,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 475.4889,
+      "step": 1220
+    },
+    {
+      "epoch": 9.460712542703758,
+      "eval_runtime": 19.5255,
+      "eval_samples_per_second": 22.125,
+      "eval_steps_per_second": 5.531,
+      "step": 1220
+    },
+    {
+      "epoch": 9.538799414348462,
+      "grad_norm": 21.528430938720703,
+      "learning_rate": 3.90625e-06,
+      "loss": 478.3553,
+      "step": 1230
+    },
+    {
+      "epoch": 9.538799414348462,
+      "eval_runtime": 19.5439,
+      "eval_samples_per_second": 22.104,
+      "eval_steps_per_second": 5.526,
+      "step": 1230
+    },
+    {
+      "epoch": 9.616886285993168,
+      "grad_norm": 21.33339500427246,
+      "learning_rate": 3.125e-06,
+      "loss": 479.5466,
+      "step": 1240
+    },
+    {
+      "epoch": 9.616886285993168,
+      "eval_runtime": 19.5446,
+      "eval_samples_per_second": 22.103,
+      "eval_steps_per_second": 5.526,
+      "step": 1240
+    },
+    {
+      "epoch": 9.694973157637872,
+      "grad_norm": 20.457260131835938,
+      "learning_rate": 2.3437500000000002e-06,
+      "loss": 469.3,
+      "step": 1250
+    },
+    {
+      "epoch": 9.694973157637872,
+      "eval_runtime": 19.5478,
+      "eval_samples_per_second": 22.1,
+      "eval_steps_per_second": 5.525,
+      "step": 1250
+    },
+    {
+      "epoch": 9.773060029282577,
+      "grad_norm": 20.839630126953125,
+      "learning_rate": 1.5625e-06,
+      "loss": 472.4047,
+      "step": 1260
+    },
+    {
+      "epoch": 9.773060029282577,
+      "eval_runtime": 19.5461,
+      "eval_samples_per_second": 22.102,
+      "eval_steps_per_second": 5.525,
+      "step": 1260
+    },
+    {
+      "epoch": 9.851146900927281,
+      "grad_norm": 21.936325073242188,
+      "learning_rate": 7.8125e-07,
+      "loss": 465.6231,
+      "step": 1270
+    },
+    {
+      "epoch": 9.851146900927281,
+      "eval_runtime": 19.5243,
+      "eval_samples_per_second": 22.126,
+      "eval_steps_per_second": 5.532,
+      "step": 1270
+    },
+    {
+      "epoch": 9.929233772571987,
+      "grad_norm": 21.870264053344727,
+      "learning_rate": 0.0,
+      "loss": 468.4088,
+      "step": 1280
+    },
+    {
+      "epoch": 9.929233772571987,
+      "eval_runtime": 19.5598,
+      "eval_samples_per_second": 22.086,
+      "eval_steps_per_second": 5.522,
+      "step": 1280
     }
   ],
   "logging_steps": 10,
@@ -1645,7 +1813,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }