Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfd0dbfd5a2e202c41c4474c701ce317f0b353244fedc30fcf9035ad3f0cfb4b
+oid sha256:95e876461f6941ed752cf45d9ac9302d2fcd14f16fa213ea0d206586aa9f8ad0
 size 2695611744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e71f4096ee32c8679f4882ef8cbd3add01377b6277f82c373625a3635016054e
+oid sha256:efc1f9e0d1f0ba25073b30251fc09e761cd12b900a86d5d2832f4e9ab7cf17ff
 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": 22.012,
       "eval_steps_per_second": 5.503,
       "step": 1160
+    },
+    {
+      "epoch": 9.070278184480234,
+      "grad_norm": 194401.953125,
+      "learning_rate": 8.59375e-06,
+      "loss": 306.9392,
+      "step": 1170
+    },
+    {
+      "epoch": 9.070278184480234,
+      "eval_runtime": 19.6327,
+      "eval_samples_per_second": 22.004,
+      "eval_steps_per_second": 5.501,
+      "step": 1170
+    },
+    {
+      "epoch": 9.14836505612494,
+      "grad_norm": 134935.84375,
+      "learning_rate": 7.8125e-06,
+      "loss": 309.7358,
+      "step": 1180
+    },
+    {
+      "epoch": 9.14836505612494,
+      "eval_runtime": 19.625,
+      "eval_samples_per_second": 22.013,
+      "eval_steps_per_second": 5.503,
+      "step": 1180
+    },
+    {
+      "epoch": 9.226451927769643,
+      "grad_norm": 169914.25,
+      "learning_rate": 7.031250000000001e-06,
+      "loss": 316.8677,
+      "step": 1190
+    },
+    {
+      "epoch": 9.226451927769643,
+      "eval_runtime": 19.6279,
+      "eval_samples_per_second": 22.01,
+      "eval_steps_per_second": 5.502,
+      "step": 1190
+    },
+    {
+      "epoch": 9.304538799414349,
+      "grad_norm": 145255.390625,
+      "learning_rate": 6.25e-06,
+      "loss": 281.0021,
+      "step": 1200
+    },
+    {
+      "epoch": 9.304538799414349,
+      "eval_runtime": 19.6322,
+      "eval_samples_per_second": 22.005,
+      "eval_steps_per_second": 5.501,
+      "step": 1200
+    },
+    {
+      "epoch": 9.382625671059053,
+      "grad_norm": 77945.0625,
+      "learning_rate": 5.46875e-06,
+      "loss": 225.1448,
+      "step": 1210
+    },
+    {
+      "epoch": 9.382625671059053,
+      "eval_runtime": 19.6173,
+      "eval_samples_per_second": 22.021,
+      "eval_steps_per_second": 5.505,
+      "step": 1210
+    },
+    {
+      "epoch": 9.460712542703758,
+      "grad_norm": 106036.7421875,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 260.6584,
+      "step": 1220
+    },
+    {
+      "epoch": 9.460712542703758,
+      "eval_runtime": 19.6147,
+      "eval_samples_per_second": 22.024,
+      "eval_steps_per_second": 5.506,
+      "step": 1220
+    },
+    {
+      "epoch": 9.538799414348462,
+      "grad_norm": 103023.9296875,
+      "learning_rate": 3.90625e-06,
+      "loss": 246.4592,
+      "step": 1230
+    },
+    {
+      "epoch": 9.538799414348462,
+      "eval_runtime": 19.6287,
+      "eval_samples_per_second": 22.009,
+      "eval_steps_per_second": 5.502,
+      "step": 1230
+    },
+    {
+      "epoch": 9.616886285993168,
+      "grad_norm": 69943.5,
+      "learning_rate": 3.125e-06,
+      "loss": 254.6815,
+      "step": 1240
+    },
+    {
+      "epoch": 9.616886285993168,
+      "eval_runtime": 19.6092,
+      "eval_samples_per_second": 22.031,
+      "eval_steps_per_second": 5.508,
+      "step": 1240
+    },
+    {
+      "epoch": 9.694973157637872,
+      "grad_norm": 157203.640625,
+      "learning_rate": 2.3437500000000002e-06,
+      "loss": 247.872,
+      "step": 1250
+    },
+    {
+      "epoch": 9.694973157637872,
+      "eval_runtime": 19.6301,
+      "eval_samples_per_second": 22.007,
+      "eval_steps_per_second": 5.502,
+      "step": 1250
+    },
+    {
+      "epoch": 9.773060029282577,
+      "grad_norm": 40032.71484375,
+      "learning_rate": 1.5625e-06,
+      "loss": 239.199,
+      "step": 1260
+    },
+    {
+      "epoch": 9.773060029282577,
+      "eval_runtime": 19.6402,
+      "eval_samples_per_second": 21.996,
+      "eval_steps_per_second": 5.499,
+      "step": 1260
+    },
+    {
+      "epoch": 9.851146900927281,
+      "grad_norm": 77447.0546875,
+      "learning_rate": 7.8125e-07,
+      "loss": 222.1013,
+      "step": 1270
+    },
+    {
+      "epoch": 9.851146900927281,
+      "eval_runtime": 19.623,
+      "eval_samples_per_second": 22.015,
+      "eval_steps_per_second": 5.504,
+      "step": 1270
+    },
+    {
+      "epoch": 9.929233772571987,
+      "grad_norm": 100750.3046875,
+      "learning_rate": 0.0,
+      "loss": 234.0448,
+      "step": 1280
+    },
+    {
+      "epoch": 9.929233772571987,
+      "eval_runtime": 19.621,
+      "eval_samples_per_second": 22.017,
+      "eval_steps_per_second": 5.504,
+      "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": {}
     }