Training in progress, step 24000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb1e4dd0903fe497764d955ecd2afbc2bc7c2a907a197c9b6156379fd0cb9d4
+oid sha256:10e75f6f68216d5e0a0d45524bf05e000b598469ccd018a2917bfcf70749be2e
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d5566af4c0c91ace25af463a9fd0c35d30ac6774693e81a743459ecd8802f15
+oid sha256:6094231b675aee692a8990e8d614035b63ad59307c785bb5adfd09bc0782c8c8
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66e48699b199955664d97c152eda4d498658e8c242bfacea1b8e34bd9e4220b
+oid sha256:1d1b2da445bdc8c10c1c9019867ae159eaa5e9b0a6d5d406fc41a87fe242c82a
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e38c3b4c9d049313a5e0f9d1718ec8e35236f2f443ecc925d89542c25ab18e0
+oid sha256:fbfd02ecdfa77e07a5c5c5775ffb7d8cd45a7a90d826fb1bf2e1490611fed3c2
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd7db22f32255632f9de493bef39e883f81b9e1f3df394e3b7c574e5214a7019
+oid sha256:4dbacae0d6cb0e8059690fc23044d3b67866df9cffa20a105496953daa6152e9
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.000233333333333,
+  "epoch": 7.000566666666666,
   "eval_steps": 500,
-  "global_step": 23500,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3298,6 +3298,76 @@
       "learning_rate": 3.4616714472682326e-06,
       "loss": 0.9235614776611328,
       "step": 23500
+    },
+    {
+      "epoch": 2.002066666666667,
+      "grad_norm": 1.5966523885726929,
+      "learning_rate": 3.4107991496373624e-06,
+      "loss": 0.27849832534790037,
+      "step": 23550
+    },
+    {
+      "epoch": 2.0037333333333334,
+      "grad_norm": 1.2076386213302612,
+      "learning_rate": 3.3602554373482532e-06,
+      "loss": 0.2752775955200195,
+      "step": 23600
+    },
+    {
+      "epoch": 2.0054,
+      "grad_norm": 1.2504218816757202,
+      "learning_rate": 3.3100417434525134e-06,
+      "loss": 0.27129779815673827,
+      "step": 23650
+    },
+    {
+      "epoch": 2.0070666666666668,
+      "grad_norm": 1.3227320909500122,
+      "learning_rate": 3.261153879385321e-06,
+      "loss": 0.2785273551940918,
+      "step": 23700
+    },
+    {
+      "epoch": 2.0087333333333333,
+      "grad_norm": 1.3441181182861328,
+      "learning_rate": 3.211597813036285e-06,
+      "loss": 0.28865924835205076,
+      "step": 23750
+    },
+    {
+      "epoch": 2.0104,
+      "grad_norm": 1.1878491640090942,
+      "learning_rate": 3.162375979928301e-06,
+      "loss": 0.3303158950805664,
+      "step": 23800
+    },
+    {
+      "epoch": 2.0120666666666667,
+      "grad_norm": 1.7056766748428345,
+      "learning_rate": 3.1134897756341128e-06,
+      "loss": 0.49927947998046873,
+      "step": 23850
+    },
+    {
+      "epoch": 2.013733333333333,
+      "grad_norm": 1.5071324110031128,
+      "learning_rate": 3.0649405862104772e-06,
+      "loss": 0.6785525512695313,
+      "step": 23900
+    },
+    {
+      "epoch": 2.0154,
+      "grad_norm": 2.0096499919891357,
+      "learning_rate": 3.0167297881588686e-06,
+      "loss": 0.6695662689208984,
+      "step": 23950
+    },
+    {
+      "epoch": 3.0007333333333333,
+      "grad_norm": 1.6812424659729004,
+      "learning_rate": 2.968858748386437e-06,
+      "loss": 0.6377016830444336,
+      "step": 24000
     }
   ],
   "logging_steps": 50,
@@ -3317,7 +3387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0965097810483773e+18,
+  "total_flos": 2.1432735901659464e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null