Training in progress, step 280000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9d65ea00f1a4532d9306cc6f4e8018944c05cd5e826ead50529858951946c8f
+oid sha256:c30841bcd23da5df2accbfd6af7df679a0f9376a5ff351a918222fc37e2df39d
 size 995605445

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab480b419c0f298e92c97801c5e30cd6bf7b2e720ec80893bd6afb26e102af44
+oid sha256:0dc7a713a7c891eea844f1039f4fde31fa20db49886276b4d9efdfb0adc4f71c
 size 510398013

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a15c47cefa9b6894ac6fc265d0b5a2c5f32b4f04f48025868ab92fe22c109d6
+oid sha256:756723c1a0732aaa05624ee70ae528bad508ab4125a6ec49d10c2305797cf89f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0850d5b39e5e46479ee0d56a5f9b2df4ff7ac65b66947c5427afcf97c554f26
+oid sha256:864fdc949856c3c644b2231c52465618168b961732a730093122274720c4b9ee
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.392650819206365,
-  "global_step": 270000,
+  "epoch": 6.629415664362155,
+  "global_step": 280000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3468,11 +3468,139 @@
       "eval_samples_per_second": 166.39,
       "eval_steps_per_second": 20.803,
       "step": 270000
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 4.976860182466775e-06,
+      "loss": 2.4924,
+      "step": 270500
+    },
+    {
+      "epoch": 6.42,
+      "learning_rate": 4.91372289042523e-06,
+      "loss": 2.484,
+      "step": 271000
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 4.850585598383686e-06,
+      "loss": 2.5076,
+      "step": 271500
+    },
+    {
+      "epoch": 6.44,
+      "learning_rate": 4.787448306342141e-06,
+      "loss": 2.4958,
+      "step": 272000
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 4.724311014300597e-06,
+      "loss": 2.4692,
+      "step": 272500
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 4.661173722259053e-06,
+      "loss": 2.4638,
+      "step": 273000
+    },
+    {
+      "epoch": 6.48,
+      "learning_rate": 4.598036430217509e-06,
+      "loss": 2.4956,
+      "step": 273500
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 4.534899138175964e-06,
+      "loss": 2.4985,
+      "step": 274000
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 4.47176184613442e-06,
+      "loss": 2.5003,
+      "step": 274500
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 4.408624554092875e-06,
+      "loss": 2.4914,
+      "step": 275000
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 4.345487262051331e-06,
+      "loss": 2.4981,
+      "step": 275500
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 4.282349970009787e-06,
+      "loss": 2.5008,
+      "step": 276000
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 4.219212677968242e-06,
+      "loss": 2.5063,
+      "step": 276500
+    },
+    {
+      "epoch": 6.56,
+      "learning_rate": 4.156075385926698e-06,
+      "loss": 2.4841,
+      "step": 277000
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 4.092938093885154e-06,
+      "loss": 2.4833,
+      "step": 277500
+    },
+    {
+      "epoch": 6.58,
+      "learning_rate": 4.029800801843609e-06,
+      "loss": 2.4839,
+      "step": 278000
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 3.966663509802065e-06,
+      "loss": 2.489,
+      "step": 278500
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 3.90352621776052e-06,
+      "loss": 2.4897,
+      "step": 279000
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 3.840388925718976e-06,
+      "loss": 2.5142,
+      "step": 279500
+    },
+    {
+      "epoch": 6.63,
+      "learning_rate": 3.7772516336774316e-06,
+      "loss": 2.4862,
+      "step": 280000
+    },
+    {
+      "epoch": 6.63,
+      "eval_loss": 3.1480441093444824,
+      "eval_runtime": 112.7656,
+      "eval_samples_per_second": 166.469,
+      "eval_steps_per_second": 20.813,
+      "step": 280000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 5.7077724099456e+16,
+  "total_flos": 5.919198694848e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab480b419c0f298e92c97801c5e30cd6bf7b2e720ec80893bd6afb26e102af44
+oid sha256:0dc7a713a7c891eea844f1039f4fde31fa20db49886276b4d9efdfb0adc4f71c
 size 510398013