Training in progress, step 1000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a54c527a33f70d78ce72260eeb46972b58e885b72ef3dfa0e6cc0f9688399f
+oid sha256:5c6171884fc5ed61ffbfa0a174a5acb2997f78839dcb07c9215894ea7eb46b3f
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd76ca7ba0bf198b8ad479ccdd911afaab0648bdaf7b3f0f15806b98b32231d0
+oid sha256:d0f0a88414d5186ed3a1e4103812e3fc4d88c6bf1e1ee04d19804baa9161d859
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21921ded89d3efb325b0f105635a2e638ac3849bf9d5ddc032cf285c7acce9df
+oid sha256:4d00a3dd4f7abe58957368cd7aff452ace8a57686fb0dac78358755bb8642321
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c3ef5862d26b8869e6c9e8a6807701995c18e51a48f7f36ceda1b5abeed0909
+oid sha256:9482f6d70f9ae4bc67feace2bbb0ecc13b0b9af42fdc5a5469cbeef07dfa096e
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ffd59099867021edcfb0ac2baab041eb4a4af12f556bedc1ab80ec65d990ef
+oid sha256:8200969ca1f32712b57dc8f347ad6b46fc031f51c43a7f55dee257c56cc13e4b
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e740bf1fa07b2703f88f14c6cf127f399fc76fbcdb55bc579c2b3e0e29cc02
+oid sha256:633d31824581e976aa18ec3d2ab0717eea67f5b90d4174990b4873ca129ad2c8
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97342e1218bd168184eb81a3ba9ece8327ff8377151f7c84b89a8ad1cc5bf7ed
+oid sha256:20282f7a7bf1d4a56474e211a37ba9dd6beebf595d753cb361e99f1f0ee0273e
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:402e70719eb092137380f0c146f2dd612f92092b503b35850f99d43e15b22645
+oid sha256:1f39c623ce268e81c5c5b4c8769dd2c43878eabeac8d8687553f3e42cf959135
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f39d1c0b40d5df607853ccb440ef174a83084d925f20ee2125e5030a6c85632
+oid sha256:1283a443ddde18cfb625127fe7c73f18da80b11341bf9bb2c96e4d2fe0266cdb
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dcd028341979c2e359a61e18bb04bf5424e94e780cb8c2f9bc4ed21b1f02b37
+oid sha256:18d72c57b4f3fbac90d20121db0f91377be19a3257d1bbb4ca0eca26155cbd95
 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": 14.552,
       "eval_steps_per_second": 1.863,
       "step": 500
+    },
+    {
+      "epoch": 0.55,
+      "eval_accuracy": 0.1651023622047244,
+      "eval_loss": 47.143985748291016,
+      "eval_runtime": 10.7415,
+      "eval_samples_per_second": 11.637,
+      "eval_steps_per_second": 1.49,
+      "step": 550
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 9027.2001953125,
+      "learning_rate": 0.0001822824974551769,
+      "loss": 1423.1790625,
+      "step": 600
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.16569291338582678,
+      "eval_loss": 47.07837677001953,
+      "eval_runtime": 8.4354,
+      "eval_samples_per_second": 14.818,
+      "eval_steps_per_second": 1.897,
+      "step": 600
+    },
+    {
+      "epoch": 0.65,
+      "eval_accuracy": 0.16648031496062993,
+      "eval_loss": 47.00508117675781,
+      "eval_runtime": 10.7099,
+      "eval_samples_per_second": 11.671,
+      "eval_steps_per_second": 1.494,
+      "step": 650
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5090.822265625,
+      "learning_rate": 0.0001115146393893927,
+      "loss": 1419.58796875,
+      "step": 700
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.16728346456692914,
+      "eval_loss": 46.935848236083984,
+      "eval_runtime": 8.4034,
+      "eval_samples_per_second": 14.875,
+      "eval_steps_per_second": 1.904,
+      "step": 700
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.1675748031496063,
+      "eval_loss": 46.88325119018555,
+      "eval_runtime": 7.7053,
+      "eval_samples_per_second": 16.223,
+      "eval_steps_per_second": 2.076,
+      "step": 750
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 8640.748046875,
+      "learning_rate": 5.269721958838045e-05,
+      "loss": 1415.78859375,
+      "step": 800
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.1682755905511811,
+      "eval_loss": 46.84225845336914,
+      "eval_runtime": 8.5769,
+      "eval_samples_per_second": 14.574,
+      "eval_steps_per_second": 1.865,
+      "step": 800
+    },
+    {
+      "epoch": 0.85,
+      "eval_accuracy": 0.16845669291338583,
+      "eval_loss": 46.823673248291016,
+      "eval_runtime": 10.5888,
+      "eval_samples_per_second": 11.805,
+      "eval_steps_per_second": 1.511,
+      "step": 850
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 14275.54296875,
+      "learning_rate": 1.3773856514840955e-05,
+      "loss": 1415.929375,
+      "step": 900
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.1687007874015748,
+      "eval_loss": 46.804019927978516,
+      "eval_runtime": 8.7116,
+      "eval_samples_per_second": 14.349,
+      "eval_steps_per_second": 1.837,
+      "step": 900
+    },
+    {
+      "epoch": 0.95,
+      "eval_accuracy": 0.16866141732283466,
+      "eval_loss": 46.80295181274414,
+      "eval_runtime": 8.0554,
+      "eval_samples_per_second": 15.518,
+      "eval_steps_per_second": 1.986,
+      "step": 950
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11099.6376953125,
+      "learning_rate": 1.3660336561915898e-09,
+      "loss": 1415.8740625,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.16873228346456692,
+      "eval_loss": 46.800193786621094,
+      "eval_runtime": 8.4996,
+      "eval_samples_per_second": 14.707,
+      "eval_steps_per_second": 1.882,
+      "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": {}
     }