Training in progress, step 290000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d7d06e2c6420caccfb1dcda8898dc956eb9f8ad24fe7c47892d4aa4fe3524bf
+oid sha256:9f3c58283d58c48daa19f5eb603db483b025adeae0cdf1cd66544ead24e8ccf7
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b167d637cc3d331f7ff3b72e6e4702ade2043062cd5ae9c61947ce023c5c60e
+oid sha256:f5699b0b7ef50cd33ac6f4846dedf2f505fecf3d7ff9d78dc3ed3e85c757275a
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
+oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
+oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
+oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
+oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
+oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
+oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
+oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45f85f2ae12e98d9620223bf7beef95656480a6afad73f6d6fb6aa192f162e4
+oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80db35d9a6af0da10cd7cebe3bf01f3932293e48fc6a8607555efe3b5591e844
+oid sha256:39bc196d8aea9810b9698ff8cd04e2aeef8774f706fbd61ae0f0055bbacd0eaf
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.245538900785154,
-  "global_step": 280000,
+  "epoch": 6.468593861527481,
+  "global_step": 290000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5606,11 +5606,211 @@
       "eval_samples_per_second": 1168.404,
       "eval_steps_per_second": 18.312,
       "step": 280000
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 0.00013777852207079235,
+      "loss": 0.2716,
+      "step": 280500
+    },
+    {
+      "epoch": 6.27,
+      "learning_rate": 0.00013730250483349825,
+      "loss": 0.2718,
+      "step": 281000
+    },
+    {
+      "epoch": 6.27,
+      "eval_loss": 0.25364091992378235,
+      "eval_runtime": 2.0184,
+      "eval_samples_per_second": 1138.006,
+      "eval_steps_per_second": 17.836,
+      "step": 281000
+    },
+    {
+      "epoch": 6.28,
+      "learning_rate": 0.00013682668113317584,
+      "loss": 0.2718,
+      "step": 281500
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 0.00013635105617335703,
+      "loss": 0.2717,
+      "step": 282000
+    },
+    {
+      "epoch": 6.29,
+      "eval_loss": 0.2546054422855377,
+      "eval_runtime": 1.9353,
+      "eval_samples_per_second": 1186.875,
+      "eval_steps_per_second": 18.601,
+      "step": 282000
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 0.00013587563515539996,
+      "loss": 0.2718,
+      "step": 282500
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 0.00013540042327843296,
+      "loss": 0.2716,
+      "step": 283000
+    },
+    {
+      "epoch": 6.31,
+      "eval_loss": 0.25594207644462585,
+      "eval_runtime": 1.9903,
+      "eval_samples_per_second": 1154.11,
+      "eval_steps_per_second": 18.088,
+      "step": 283000
+    },
+    {
+      "epoch": 6.32,
+      "learning_rate": 0.00013492542573929678,
+      "loss": 0.2718,
+      "step": 283500
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 0.00013445064773248846,
+      "loss": 0.2718,
+      "step": 284000
+    },
+    {
+      "epoch": 6.33,
+      "eval_loss": 0.25390535593032837,
+      "eval_runtime": 1.9996,
+      "eval_samples_per_second": 1148.745,
+      "eval_steps_per_second": 18.004,
+      "step": 284000
+    },
+    {
+      "epoch": 6.35,
+      "learning_rate": 0.00013397609445010432,
+      "loss": 0.2711,
+      "step": 284500
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 0.00013350177108178288,
+      "loss": 0.2715,
+      "step": 285000
+    },
+    {
+      "epoch": 6.36,
+      "eval_loss": 0.2538110613822937,
+      "eval_runtime": 2.0098,
+      "eval_samples_per_second": 1142.879,
+      "eval_steps_per_second": 17.912,
+      "step": 285000
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 0.00013302768281464863,
+      "loss": 0.2713,
+      "step": 285500
+    },
+    {
+      "epoch": 6.38,
+      "learning_rate": 0.0001325538348332548,
+      "loss": 0.2713,
+      "step": 286000
+    },
+    {
+      "epoch": 6.38,
+      "eval_loss": 0.2533688545227051,
+      "eval_runtime": 1.9973,
+      "eval_samples_per_second": 1150.057,
+      "eval_steps_per_second": 18.024,
+      "step": 286000
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 0.00013208023231952706,
+      "loss": 0.2711,
+      "step": 286500
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 0.0001316068804527066,
+      "loss": 0.271,
+      "step": 287000
+    },
+    {
+      "epoch": 6.4,
+      "eval_loss": 0.25663408637046814,
+      "eval_runtime": 2.0033,
+      "eval_samples_per_second": 1146.595,
+      "eval_steps_per_second": 17.97,
+      "step": 287000
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 0.00013113378440929353,
+      "loss": 0.2709,
+      "step": 287500
+    },
+    {
+      "epoch": 6.42,
+      "learning_rate": 0.00013066094936299056,
+      "loss": 0.2707,
+      "step": 288000
+    },
+    {
+      "epoch": 6.42,
+      "eval_loss": 0.2554568946361542,
+      "eval_runtime": 1.9451,
+      "eval_samples_per_second": 1180.915,
+      "eval_steps_per_second": 18.508,
+      "step": 288000
+    },
+    {
+      "epoch": 6.44,
+      "learning_rate": 0.00013018838048464582,
+      "loss": 0.271,
+      "step": 288500
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 0.00012971608294219702,
+      "loss": 0.2709,
+      "step": 289000
+    },
+    {
+      "epoch": 6.45,
+      "eval_loss": 0.2539980113506317,
+      "eval_runtime": 2.0049,
+      "eval_samples_per_second": 1145.67,
+      "eval_steps_per_second": 17.956,
+      "step": 289000
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 0.00012924406190061423,
+      "loss": 0.2707,
+      "step": 289500
+    },
+    {
+      "epoch": 6.47,
+      "learning_rate": 0.0001287723225218441,
+      "loss": 0.2706,
+      "step": 290000
+    },
+    {
+      "epoch": 6.47,
+      "eval_loss": 0.2525833547115326,
+      "eval_runtime": 1.9728,
+      "eval_samples_per_second": 1164.356,
+      "eval_steps_per_second": 18.249,
+      "step": 290000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 8.945469160117508e+21,
+  "total_flos": 9.264956298892008e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b167d637cc3d331f7ff3b72e6e4702ade2043062cd5ae9c61947ce023c5c60e
+oid sha256:f5699b0b7ef50cd33ac6f4846dedf2f505fecf3d7ff9d78dc3ed3e85c757275a
 size 102501541