Training in progress, step 75000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62aa43a334d172b6c92a9e86cddc4224139d388495104b8bc9cf342a33dbaa32
+oid sha256:1be4e3f0b7af06ec1e6538d46507b80fedb0171969b37b72db0eba79d5f0d3d2
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e85e1be18414fd56bd482ec51088607f1f3b26827e8774a78e7680201613c3
+oid sha256:5f4389ea379943d9d4b8573e14c7deeab31306f43d499adfcb327ee497b5df6b
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563f94766f626d38c33a896bb938f939d6c275e108ea7b534c0d209b4993de23
+oid sha256:1563476cd29a59353ff98b7b6e958a4a29dc72d9a687649be94fb8e5bac19669
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18896310f2ee7059609508aec0a182eb327bcb160c37b740bb26bfe558c18ac5
+oid sha256:6b2e4b8e9a822377ddf0c372a8490d7f72aef8f4376ac7e86d78dd73996019e6
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72eb753390b21928e56a04c9cc3484c55b2eccd5187fb0f52710f912f93a98d9
+oid sha256:78ee8c1ce964536f6e2f2aba1e65041b49ceef1bcf954e778c5ffc17b2663e66
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.09437576179697,
-  "global_step": 70000,
+  "epoch": 6.52968831621104,
+  "global_step": 75000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -958,11 +958,79 @@
       "eval_samples_per_second": 292.674,
       "eval_steps_per_second": 4.624,
       "step": 70000
+    },
+    {
+      "epoch": 6.14,
+      "learning_rate": 2.8166833668202425e-05,
+      "loss": 0.4067,
+      "step": 70500
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 2.759969559696268e-05,
+      "loss": 0.4077,
+      "step": 71000
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 2.703941452170851e-05,
+      "loss": 0.408,
+      "step": 71500
+    },
+    {
+      "epoch": 6.27,
+      "learning_rate": 2.648722818281383e-05,
+      "loss": 0.4066,
+      "step": 72000
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 2.594105969789391e-05,
+      "loss": 0.4067,
+      "step": 72500
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 2.5402157452548983e-05,
+      "loss": 0.4072,
+      "step": 73000
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 2.487065441284431e-05,
+      "loss": 0.4074,
+      "step": 73500
+    },
+    {
+      "epoch": 6.44,
+      "learning_rate": 2.434772206306137e-05,
+      "loss": 0.4067,
+      "step": 74000
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 2.3831393550873072e-05,
+      "loss": 0.4066,
+      "step": 74500
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 2.3322851806813925e-05,
+      "loss": 0.4065,
+      "step": 75000
+    },
+    {
+      "epoch": 6.53,
+      "eval_loss": 0.38793495297431946,
+      "eval_runtime": 17.4149,
+      "eval_samples_per_second": 287.111,
+      "eval_steps_per_second": 4.536,
+      "step": 75000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 3.296791220814238e+21,
+  "total_flos": 3.532284288179e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e85e1be18414fd56bd482ec51088607f1f3b26827e8774a78e7680201613c3
+oid sha256:5f4389ea379943d9d4b8573e14c7deeab31306f43d499adfcb327ee497b5df6b
 size 449471589