Training in progress, step 1000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bade0394fffddee210809f85ef580bee9253cbdc63658c93609636b50849132
+oid sha256:46934af3573871dfea7d1989ce9b5dd2fc88d7029cc7a29aa49696756084cc0b
 size 2252747

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb28c9de07f152f7162a5afb9fa57feec1bb26c13b04027682db0fc06632987
+oid sha256:d7c1dfd3789b6cb9dac5da1f24dc7017774f6db9b41bfae170b2278be51dd4a9
 size 847648963

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76e07cf0345bf512c151f0957ea0731d69830b690d0d47fe9335a01fd87ff0d5
+oid sha256:24d48aa92727987083d0bcdd5037110e1c878d41da32b90284910b671afdf5b0
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b1e066d0ede72061c950708a201039b55678b711860b01a8850b06ca136b2f7
+oid sha256:d2b754989164ed24b1fd5d21f43dcf0c273ff72d7fdf3d4c2bf4517be9438f53
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c83436d7d707c3d61b15981b0298ffc689a42626328497b706511643f5ceb662
+oid sha256:457a2882dad2249a075d16bc60a9d6f1d02fc6534344eb7069865c9dd06c7024
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcdd3e13e6b97f6783c4798cd70e6e48a2104ccaacf287e70c62bf0c09ec3f22
+oid sha256:5f32f9ecfb130472de30af5085eb848eedececce5481930e500b29d06331cb2e
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa71eeae497ae80be5331ba680216cbc540af220332f0c56f028ebfc2f445e20
+oid sha256:c686ae05e681a5d90696b0c260ad0fb0b06594229199d0b2ed64aea2a4664f46
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70b31dc63a3cc8a092a19500455139bf70b0744911cd2bfd2067660e23a2f80
+oid sha256:57ea3dd399ed721886bd76b064bb8fded9d7d8d28cb68a0c9435c18657bd1132
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b86db638d3fa6bb27db28786ecb6ac4913c0fd4a25f7498fd0ae3429244b41eb
+oid sha256:593b9d9100c58eedd0625fa647d716d43154cc6c9f18b0a07aa72c501f7dc81f
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840457dd3ad214440eed9722d63d2231facaf5d2730c8917e33dd9d3a6078932
+oid sha256:e068abc8d6faa0b30472d1c0b5bc53e44130d902bf93caa9b4deb6ce1ebb1d9f
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b79cc0df1e63ecef3adaaf8ef4c455eb58ccb70431c624030057057995b60a8
+oid sha256:94b7b1a014f5dad743694fda5858015bfe3bd4c82eac608d649238b91858a560
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 1.0,
   "eval_steps": 50,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -133,6 +133,131 @@
       "eval_samples_per_second": 13.361,
       "eval_steps_per_second": 1.71,
       "step": 500
+    },
+    {
+      "epoch": 0.55,
+      "eval_accuracy": 0.19033070866141732,
+      "eval_loss": 44.91364288330078,
+      "eval_runtime": 8.7783,
+      "eval_samples_per_second": 14.24,
+      "eval_steps_per_second": 1.823,
+      "step": 550
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 28925.150390625,
+      "learning_rate": 0.0001822824974551769,
+      "loss": 1365.12171875,
+      "step": 600
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.19299212598425197,
+      "eval_loss": 44.67140579223633,
+      "eval_runtime": 9.3914,
+      "eval_samples_per_second": 13.31,
+      "eval_steps_per_second": 1.704,
+      "step": 600
+    },
+    {
+      "epoch": 0.65,
+      "eval_accuracy": 0.19476377952755905,
+      "eval_loss": 44.36285400390625,
+      "eval_runtime": 11.8603,
+      "eval_samples_per_second": 10.539,
+      "eval_steps_per_second": 1.349,
+      "step": 650
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 6494.93701171875,
+      "learning_rate": 0.0001115146393893927,
+      "loss": 1348.1965625,
+      "step": 700
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.19607086614173228,
+      "eval_loss": 44.26563262939453,
+      "eval_runtime": 9.2536,
+      "eval_samples_per_second": 13.508,
+      "eval_steps_per_second": 1.729,
+      "step": 700
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.19792125984251968,
+      "eval_loss": 44.026851654052734,
+      "eval_runtime": 13.9865,
+      "eval_samples_per_second": 8.937,
+      "eval_steps_per_second": 1.144,
+      "step": 750
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6566.00732421875,
+      "learning_rate": 5.269721958838045e-05,
+      "loss": 1335.25640625,
+      "step": 800
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.19969291338582676,
+      "eval_loss": 43.83841323852539,
+      "eval_runtime": 9.3886,
+      "eval_samples_per_second": 13.314,
+      "eval_steps_per_second": 1.704,
+      "step": 800
+    },
+    {
+      "epoch": 0.85,
+      "eval_accuracy": 0.2002755905511811,
+      "eval_loss": 43.76130294799805,
+      "eval_runtime": 16.2687,
+      "eval_samples_per_second": 7.683,
+      "eval_steps_per_second": 0.983,
+      "step": 850
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5925.8193359375,
+      "learning_rate": 1.3773856514840955e-05,
+      "loss": 1328.743125,
+      "step": 900
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.20086614173228345,
+      "eval_loss": 43.69052505493164,
+      "eval_runtime": 9.3216,
+      "eval_samples_per_second": 13.41,
+      "eval_steps_per_second": 1.716,
+      "step": 900
+    },
+    {
+      "epoch": 0.95,
+      "eval_accuracy": 0.2008503937007874,
+      "eval_loss": 43.665740966796875,
+      "eval_runtime": 15.4653,
+      "eval_samples_per_second": 8.083,
+      "eval_steps_per_second": 1.035,
+      "step": 950
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6814.45703125,
+      "learning_rate": 1.3660336561915898e-09,
+      "loss": 1325.8203125,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.2012047244094488,
+      "eval_loss": 43.653385162353516,
+      "eval_runtime": 9.352,
+      "eval_samples_per_second": 13.366,
+      "eval_steps_per_second": 1.711,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -147,7 +272,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }