Training in progress, step 275, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b30428edb2ec353fb00d980723dab87d47a3a57a437c530816fd877e52bf44df
+oid sha256:67d3498e837d0f50c42422fc84f1f7baafb513956ff5819ed74aa854a3f03ca9
 size 6171927112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:573f39757dc714be30e45637a17b4dc1aaf790d8c76a677b9cc40389734d5bbc
+oid sha256:f0bc7c892ca343b720a60812170b7c972378e9279e1b626c85c799d1abdf71c3
 size 12344133221

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:715563349ae345b2e3188b314e826936503719f9ac8cb3873b644d2566f112eb
+oid sha256:9c125ae2c56e328b466f25a9167f095fce27b7bcd4cd7957a7b20020419f7855
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26666666666666666,
+  "epoch": 0.09651662718259191,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 275,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,10 +148,59 @@
       "learning_rate": 1.768888888888889e-05,
       "loss": 4.100537109375,
       "step": 200
+    },
+    {
+      "epoch": 0.0737036062121611,
+      "grad_norm": 5.625,
+      "learning_rate": 4.888888888888889e-06,
+      "loss": 6.024441146850586,
+      "step": 210
+    },
+    {
+      "epoch": 0.07721330174607353,
+      "grad_norm": 5.96875,
+      "learning_rate": 5.12280701754386e-06,
+      "loss": 5.444968414306641,
+      "step": 220
+    },
+    {
+      "epoch": 0.08072299727998596,
+      "grad_norm": 5.78125,
+      "learning_rate": 5.356725146198831e-06,
+      "loss": 5.957166290283203,
+      "step": 230
+    },
+    {
+      "epoch": 0.08423269281389839,
+      "grad_norm": 3.484375,
+      "learning_rate": 5.590643274853802e-06,
+      "loss": 5.767229080200195,
+      "step": 240
+    },
+    {
+      "epoch": 0.08774238834781083,
+      "grad_norm": 6.25,
+      "learning_rate": 5.824561403508773e-06,
+      "loss": 5.761946487426758,
+      "step": 250
+    },
+    {
+      "epoch": 0.09125208388172326,
+      "grad_norm": 8.375,
+      "learning_rate": 6.058479532163744e-06,
+      "loss": 5.641996765136719,
+      "step": 260
+    },
+    {
+      "epoch": 0.0947617794156357,
+      "grad_norm": 4.9375,
+      "learning_rate": 6.292397660818715e-06,
+      "loss": 5.592499542236328,
+      "step": 270
     }
   ],
   "logging_steps": 10,
-  "max_steps": 2250,
+  "max_steps": 8550,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 25,
@@ -167,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.36434175524864e+17,
+  "total_flos": 6.00096991346688e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null