Training in progress, step 12000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96559e121960210b371c3fcc350fdad69dc4bebab11e0e85ac5587d763377e3f
+oid sha256:1ce9c46d557572f4fcbc07e928118f6cc62e0b5e8cf31db266fe95263ba3e76e
 size 3871543575

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c726760f8cdd1ac918cb7b580cc42cc2847406cb9b68f2a0b2c79df0062d1b
+oid sha256:1d1f16b9499b183fd135e35ee2be76d0e985c671a548c4533e1070a1ad1fda4c
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea2fc25e8860dfffb4f2ed8f3fbd28f04f1afe41b93499531ba6c38f0c37deb4
-size 14575
+oid sha256:2bb1d6e54f0324da11c5e276691517a42f4406f1c713402142fa0cb1d5e4fb8e
+size 14511

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d79de33a1dadebecdc6710fbbebc54394b36ff40dc16ce7c4b9cd325b8d41b2
+oid sha256:26e112e52be32db4475359f181f3667920cb1d8e46dd64824e1aaf37332cbe6f
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b7f7dd47f8776cb11bf81d14503503a8691f27074ccc97afc806b0f50fc73d
+oid sha256:f2a0beb0c18c47fc766521ab3d6dfc7f37dbeabbef4cec76b8c279a9d35a1e9e
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20970735338834656,
-  "global_step": 8000,
+  "epoch": 0.31456103008251984,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,11 +102,59 @@
       "learning_rate": 4.477036903377901e-05,
       "loss": 1.4986,
       "step": 8000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.412373343543317e-05,
+      "loss": 1.4854,
+      "step": 8500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.3446067955536154e-05,
+      "loss": 1.4922,
+      "step": 9000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.273580569980726e-05,
+      "loss": 1.5026,
+      "step": 9500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.199547674398644e-05,
+      "loss": 1.5012,
+      "step": 10000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.1226336133886704e-05,
+      "loss": 1.492,
+      "step": 10500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.04296877584006e-05,
+      "loss": 1.4902,
+      "step": 11000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.9606882139077016e-05,
+      "loss": 1.4784,
+      "step": 11500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.876275184846879e-05,
+      "loss": 1.4809,
+      "step": 12000
     }
   ],
   "max_steps": 38148,
   "num_train_epochs": 1,
-  "total_flos": 8864585817513984.0,
+  "total_flos": 1.327204485033984e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c726760f8cdd1ac918cb7b580cc42cc2847406cb9b68f2a0b2c79df0062d1b
+oid sha256:1d1f16b9499b183fd135e35ee2be76d0e985c671a548c4533e1070a1ad1fda4c
 size 1944201353

runs/Jun16_09-47-04_1a3b54f65ca2/events.out.tfevents.1686908851.1a3b54f65ca2.10028.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99a357266e63efac109efc4f27c9701e51837c5f584c4f5ea21dfd3f62d8d36f
-size 6974
+oid sha256:a57b6a31592e76e7013c9b3338396fe0f54e5f2676de83120975696c638af21d
+size 8230