Training in progress, step 80000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1be4e3f0b7af06ec1e6538d46507b80fedb0171969b37b72db0eba79d5f0d3d2
+oid sha256:13f88c1653eaee71905eff10c477ade80a8231b1852fd24fc1d8070feadbe867
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4389ea379943d9d4b8573e14c7deeab31306f43d499adfcb327ee497b5df6b
+oid sha256:287c54a7fb259d9a27424e770b3fdfa09912688280150c514400ad14fd8b8e71
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1563476cd29a59353ff98b7b6e958a4a29dc72d9a687649be94fb8e5bac19669
+oid sha256:9ec9444070936ff912e17b8bf39a488fe9c3508ab66a9f8cc8090cbf033a8133
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b2e4b8e9a822377ddf0c372a8490d7f72aef8f4376ac7e86d78dd73996019e6
+oid sha256:eda0fb0016a5517f1c8a7137584fb99d1503d53e8d61b84aafd902b7463f3a6d
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ee8c1ce964536f6e2f2aba1e65041b49ceef1bcf954e778c5ffc17b2663e66
+oid sha256:68e5bc2866367788ff40bed8e1205d239c8a00166e6a17a9ac8e287f80b514c7
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.52968831621104,
-  "global_step": 75000,
+  "epoch": 6.965000870625109,
+  "global_step": 80000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1026,11 +1026,79 @@
       "eval_samples_per_second": 287.111,
       "eval_steps_per_second": 4.536,
       "step": 75000
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 2.282222230594981e-05,
+      "loss": 0.4061,
+      "step": 75500
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 2.2329628571118985e-05,
+      "loss": 0.4064,
+      "step": 76000
+    },
+    {
+      "epoch": 6.66,
+      "learning_rate": 2.1845192142454672e-05,
+      "loss": 0.4056,
+      "step": 76500
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 2.1369976527875413e-05,
+      "loss": 0.4055,
+      "step": 77000
+    },
+    {
+      "epoch": 6.75,
+      "learning_rate": 2.0902194347163136e-05,
+      "loss": 0.4048,
+      "step": 77500
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 2.0442921670652984e-05,
+      "loss": 0.4054,
+      "step": 78000
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 1.999227181700563e-05,
+      "loss": 0.4054,
+      "step": 78500
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 1.9551231019628344e-05,
+      "loss": 0.4043,
+      "step": 79000
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 1.9118140436571432e-05,
+      "loss": 0.4051,
+      "step": 79500
+    },
+    {
+      "epoch": 6.97,
+      "learning_rate": 1.869399954632371e-05,
+      "loss": 0.4044,
+      "step": 80000
+    },
+    {
+      "epoch": 6.97,
+      "eval_loss": 0.38538074493408203,
+      "eval_runtime": 17.7787,
+      "eval_samples_per_second": 281.235,
+      "eval_steps_per_second": 4.444,
+      "step": 80000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 3.532284288179e+21,
+  "total_flos": 3.7677773555437614e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4389ea379943d9d4b8573e14c7deeab31306f43d499adfcb327ee497b5df6b
+oid sha256:287c54a7fb259d9a27424e770b3fdfa09912688280150c514400ad14fd8b8e71
 size 449471589