Training in progress, step 85000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f88c1653eaee71905eff10c477ade80a8231b1852fd24fc1d8070feadbe867
+oid sha256:991fa5d4e5f5edee4c8ef0d2412d108fe8823401ec1d29bf753ff58c6250ef3e
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:287c54a7fb259d9a27424e770b3fdfa09912688280150c514400ad14fd8b8e71
+oid sha256:11bb76b4f4b7c201591694a6bcc8c84f8d309b1f1cea21af022f918961a63b4e
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ec9444070936ff912e17b8bf39a488fe9c3508ab66a9f8cc8090cbf033a8133
+oid sha256:194884037966e731fcb91766eca35472e355bcdf78ecca2ffbee8cb9b09126dd
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eda0fb0016a5517f1c8a7137584fb99d1503d53e8d61b84aafd902b7463f3a6d
+oid sha256:8ec9980e0e4d49a11c107c88863e01c8ed67819546b646e61e0a1dcaaf5d9232
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68e5bc2866367788ff40bed8e1205d239c8a00166e6a17a9ac8e287f80b514c7
+oid sha256:5312022d6e3da19908b0afff153bcac2a5b0f2f58c4dfc36e2fe367687099b95
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.965000870625109,
-  "global_step": 80000,
+  "epoch": 7.400313425039178,
+  "global_step": 85000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1094,11 +1094,79 @@
       "eval_samples_per_second": 281.235,
       "eval_steps_per_second": 4.444,
       "step": 80000
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 1.8278912999303293e-05,
+      "loss": 0.4046,
+      "step": 80500
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 1.7873785866083376e-05,
+      "loss": 0.4039,
+      "step": 81000
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 1.747709438313117e-05,
+      "loss": 0.4041,
+      "step": 81500
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 1.7089757496546325e-05,
+      "loss": 0.4029,
+      "step": 82000
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 1.671187077590979e-05,
+      "loss": 0.4031,
+      "step": 82500
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 1.6343527459115402e-05,
+      "loss": 0.404,
+      "step": 83000
+    },
+    {
+      "epoch": 7.27,
+      "learning_rate": 1.5985526173180873e-05,
+      "loss": 0.4021,
+      "step": 83500
+    },
+    {
+      "epoch": 7.31,
+      "learning_rate": 1.563652040423561e-05,
+      "loss": 0.4028,
+      "step": 84000
+    },
+    {
+      "epoch": 7.36,
+      "learning_rate": 1.5297323365745916e-05,
+      "loss": 0.4028,
+      "step": 84500
+    },
+    {
+      "epoch": 7.4,
+      "learning_rate": 1.496801874950552e-05,
+      "loss": 0.403,
+      "step": 85000
+    },
+    {
+      "epoch": 7.4,
+      "eval_loss": 0.3836823105812073,
+      "eval_runtime": 17.7691,
+      "eval_samples_per_second": 281.388,
+      "eval_steps_per_second": 4.446,
+      "step": 85000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 3.7677773555437614e+21,
+  "total_flos": 4.0032518025264523e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:287c54a7fb259d9a27424e770b3fdfa09912688280150c514400ad14fd8b8e71
+oid sha256:11bb76b4f4b7c201591694a6bcc8c84f8d309b1f1cea21af022f918961a63b4e
 size 449471589