Training in progress, step 6500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5273b6699320981461500e4af62c20b70bef9d60a11b29e370cfe9d83dc7681
+oid sha256:cc52f4e64e8952deb71cc763f4b37e39d00cf464379459d719f6459b125471e6
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a197c202c578be20062bb70243bde302cb2480d71bf0e2c37d260df3605f1a02
+oid sha256:60680ad87cf6e00d17289e3fd4f5fd0a946cf33df8b77b2f6ae280d4cede4843
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f621c40c37c796d75663f728f7490ddcd9db068eaa82d92691bb9a37ff256f
+oid sha256:b928d2d8033ac6bd87c58a39b741faace8bd1c6b0d070b7fad23c19520ff9f1a
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
+oid sha256:72ec040f7dbfafb8a0d9c346b901cc53a9760e25574232230ec90bf3c4a5f84d
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dccdfccabdb48680f1489db82bd4ed2bc1d6584eefbc4a5a787078d65373f2e
+oid sha256:d2fda80b4e4bf89372eb5708338537be5c37b5055dbaaea7c079560e27207b63
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.011033333333334,
+  "epoch": 9.012733333333333,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -848,6 +848,76 @@
       "learning_rate": 2.750059176923248e-05,
       "loss": 0.4137184524536133,
       "step": 6000
+    },
+    {
+      "epoch": 2.0035,
+      "grad_norm": 1.9652310609817505,
+      "learning_rate": 2.745626915940975e-05,
+      "loss": 0.46977787017822265,
+      "step": 6050
+    },
+    {
+      "epoch": 2.0051666666666668,
+      "grad_norm": 1.7700436115264893,
+      "learning_rate": 2.7411593380502133e-05,
+      "loss": 0.463070182800293,
+      "step": 6100
+    },
+    {
+      "epoch": 2.0068333333333332,
+      "grad_norm": 1.8935976028442383,
+      "learning_rate": 2.7366565699189398e-05,
+      "loss": 0.44758522033691406,
+      "step": 6150
+    },
+    {
+      "epoch": 2.0085,
+      "grad_norm": 1.3832303285598755,
+      "learning_rate": 2.732118739212868e-05,
+      "loss": 0.4535627746582031,
+      "step": 6200
+    },
+    {
+      "epoch": 2.0101666666666667,
+      "grad_norm": 1.6829535961151123,
+      "learning_rate": 2.7275459745918316e-05,
+      "loss": 0.48570785522460935,
+      "step": 6250
+    },
+    {
+      "epoch": 2.011833333333333,
+      "grad_norm": 1.8293315172195435,
+      "learning_rate": 2.722938405706136e-05,
+      "loss": 0.5032914352416992,
+      "step": 6300
+    },
+    {
+      "epoch": 2.0135,
+      "grad_norm": 1.7647825479507446,
+      "learning_rate": 2.7182961631928812e-05,
+      "loss": 0.5367673110961914,
+      "step": 6350
+    },
+    {
+      "epoch": 3.0002,
+      "grad_norm": 1.6019330024719238,
+      "learning_rate": 2.7136193786722592e-05,
+      "loss": 0.5786269378662109,
+      "step": 6400
+    },
+    {
+      "epoch": 3.0018666666666665,
+      "grad_norm": 1.6498947143554688,
+      "learning_rate": 2.7089081847438228e-05,
+      "loss": 0.6523352813720703,
+      "step": 6450
+    },
+    {
+      "epoch": 3.0035333333333334,
+      "grad_norm": 2.055866241455078,
+      "learning_rate": 2.7041627149827236e-05,
+      "loss": 0.6170930862426758,
+      "step": 6500
     }
   ],
   "logging_steps": 50,
@@ -867,7 +937,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.3536156823924736e+17,
+  "total_flos": 5.799930673615503e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null