Upload 8 files

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a226fcc947eec5a7ecf7755fe07a0e2398ca9bfd23c98493eb22879f4c702c1d
+oid sha256:ae132a4a670d70c2365439b1b32f73578bbe513edd2e0299f01ea1302af81f0c
 size 655342981

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f5a6d7915f9dee44fe610451a7f8d7525d5e60d700f17af21240683111649c
+oid sha256:95508259f48f41c3e02cf1556a1f27bbe48a513f6d862c8a7b3910ae72acee38
 size 333968953

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e758cb98894568f912ef81c5d40385e49e7d85140a2098a83844399fed337b4
+oid sha256:708c0633fc2806448a36d54172c18b6fbe465f892fb67e669ae170a4b5034cdf
 size 13553

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c10e76378cf039e5e8914bbf970cc36e6d097abfa79ea4180870a8d3b18ccc
+oid sha256:6bf45a7cece26021363c348414b2495d0d387d9868ac402ae5067b6d6efc43b5
 size 627

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6775005242189138,
-  "global_step": 8000,
+  "epoch": 2.935625917383099,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -110,11 +110,91 @@
       "learning_rate": 8.816663171873909e-06,
       "loss": 1.2822,
       "step": 8000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 8.117704620116029e-06,
+      "loss": 1.2721,
+      "step": 8500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 7.418746068358147e-06,
+      "loss": 1.2596,
+      "step": 9000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 6.719787516600266e-06,
+      "loss": 1.2635,
+      "step": 9500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.3475877046585083,
+      "eval_runtime": 2879.1327,
+      "eval_samples_per_second": 12.22,
+      "eval_steps_per_second": 1.528,
+      "step": 9538
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 6.020828964842386e-06,
+      "loss": 1.2592,
+      "step": 10000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 5.321870413084504e-06,
+      "loss": 1.2459,
+      "step": 10500
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 4.6229118613266235e-06,
+      "loss": 1.2477,
+      "step": 11000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 3.923953309568743e-06,
+      "loss": 1.249,
+      "step": 11500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 3.224994757810862e-06,
+      "loss": 1.2376,
+      "step": 12000
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 2.5260362060529814e-06,
+      "loss": 1.238,
+      "step": 12500
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.8270776542951004e-06,
+      "loss": 1.2409,
+      "step": 13000
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.1281191025372195e-06,
+      "loss": 1.2365,
+      "step": 13500
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 4.291605507793388e-07,
+      "loss": 1.237,
+      "step": 14000
     }
   ],
   "max_steps": 14307,
   "num_train_epochs": 3,
-  "total_flos": 2090210694266880.0,
+  "total_flos": 3657827887349760.0,
   "trial_name": null,
   "trial_params": null
 }