checkpoint

{checkpoint-6176 → checkpoint-7334}/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8019737696403064,
+  "epoch": 0.9523438514478639,
   "eval_steps": 500,
-  "global_step": 6176,
+  "global_step": 7334,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -869,6 +869,167 @@
       "learning_rate": 1.702723325878174e-05,
       "loss": 0.1903,
       "step": 6150
+    },
+    {
+      "epoch": 0.8050902480197377,
+      "grad_norm": 0.5991400480270386,
+      "learning_rate": 1.700092093145639e-05,
+      "loss": 0.197,
+      "step": 6200
+    },
+    {
+      "epoch": 0.8115829113102194,
+      "grad_norm": 0.9522245526313782,
+      "learning_rate": 1.6974608604131037e-05,
+      "loss": 0.1962,
+      "step": 6250
+    },
+    {
+      "epoch": 0.8180755746007012,
+      "grad_norm": 0.8645381927490234,
+      "learning_rate": 1.6948296276805686e-05,
+      "loss": 0.1901,
+      "step": 6300
+    },
+    {
+      "epoch": 0.8245682378911829,
+      "grad_norm": 0.5243034958839417,
+      "learning_rate": 1.6921983949480334e-05,
+      "loss": 0.194,
+      "step": 6350
+    },
+    {
+      "epoch": 0.8310609011816648,
+      "grad_norm": 0.5842151641845703,
+      "learning_rate": 1.6895671622154982e-05,
+      "loss": 0.1917,
+      "step": 6400
+    },
+    {
+      "epoch": 0.8375535644721465,
+      "grad_norm": 0.6111485362052917,
+      "learning_rate": 1.6869359294829627e-05,
+      "loss": 0.2042,
+      "step": 6450
+    },
+    {
+      "epoch": 0.8440462277626283,
+      "grad_norm": 0.6515288949012756,
+      "learning_rate": 1.684304696750428e-05,
+      "loss": 0.2032,
+      "step": 6500
+    },
+    {
+      "epoch": 0.85053889105311,
+      "grad_norm": 0.7596396207809448,
+      "learning_rate": 1.6816734640178924e-05,
+      "loss": 0.193,
+      "step": 6550
+    },
+    {
+      "epoch": 0.8570315543435918,
+      "grad_norm": 0.6944254636764526,
+      "learning_rate": 1.6790422312853575e-05,
+      "loss": 0.1899,
+      "step": 6600
+    },
+    {
+      "epoch": 0.8635242176340735,
+      "grad_norm": 0.6190508604049683,
+      "learning_rate": 1.676410998552822e-05,
+      "loss": 0.1987,
+      "step": 6650
+    },
+    {
+      "epoch": 0.8700168809245552,
+      "grad_norm": 1.1515477895736694,
+      "learning_rate": 1.673779765820287e-05,
+      "loss": 0.196,
+      "step": 6700
+    },
+    {
+      "epoch": 0.876509544215037,
+      "grad_norm": 0.5803254842758179,
+      "learning_rate": 1.6711485330877517e-05,
+      "loss": 0.1923,
+      "step": 6750
+    },
+    {
+      "epoch": 0.8830022075055187,
+      "grad_norm": 0.8052871227264404,
+      "learning_rate": 1.6685173003552165e-05,
+      "loss": 0.1894,
+      "step": 6800
+    },
+    {
+      "epoch": 0.8894948707960005,
+      "grad_norm": 0.9313941597938538,
+      "learning_rate": 1.6658860676226813e-05,
+      "loss": 0.1889,
+      "step": 6850
+    },
+    {
+      "epoch": 0.8959875340864822,
+      "grad_norm": 0.5186671614646912,
+      "learning_rate": 1.663254834890146e-05,
+      "loss": 0.1895,
+      "step": 6900
+    },
+    {
+      "epoch": 0.902480197376964,
+      "grad_norm": 0.7533177137374878,
+      "learning_rate": 1.660623602157611e-05,
+      "loss": 0.1956,
+      "step": 6950
+    },
+    {
+      "epoch": 0.9089728606674458,
+      "grad_norm": 0.7142027020454407,
+      "learning_rate": 1.6579923694250758e-05,
+      "loss": 0.1921,
+      "step": 7000
+    },
+    {
+      "epoch": 0.9154655239579276,
+      "grad_norm": 1.0748203992843628,
+      "learning_rate": 1.6553611366925407e-05,
+      "loss": 0.1847,
+      "step": 7050
+    },
+    {
+      "epoch": 0.9219581872484093,
+      "grad_norm": 0.5605922341346741,
+      "learning_rate": 1.6527299039600055e-05,
+      "loss": 0.1887,
+      "step": 7100
+    },
+    {
+      "epoch": 0.9284508505388911,
+      "grad_norm": 0.5474116802215576,
+      "learning_rate": 1.6500986712274703e-05,
+      "loss": 0.1948,
+      "step": 7150
+    },
+    {
+      "epoch": 0.9349435138293728,
+      "grad_norm": 0.9507768154144287,
+      "learning_rate": 1.6474674384949348e-05,
+      "loss": 0.2126,
+      "step": 7200
+    },
+    {
+      "epoch": 0.9414361771198546,
+      "grad_norm": 0.694097101688385,
+      "learning_rate": 1.6448362057624e-05,
+      "loss": 0.1904,
+      "step": 7250
+    },
+    {
+      "epoch": 0.9479288404103363,
+      "grad_norm": 0.6153343915939331,
+      "learning_rate": 1.6422049730298645e-05,
+      "loss": 0.1921,
+      "step": 7300
     }
   ],
   "logging_steps": 50,
@@ -888,7 +1049,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.1647602330330726e+17,
+  "total_flos": 6.133152775887913e+17,
   "train_batch_size": 40,
   "trial_name": null,
   "trial_params": null