Training in progress, step 14500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a0713db12d6152b8cfeeba9b02564da21994ad2fa97b47ec225f9ad5fd0fee
+oid sha256:639309c67ebf73e5325dfc52be87bdaf34983155f0ad8c1947201f1e8df5f743
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f64184e91e91ec566da9dfdf6d38d2c719ffc81fa39bd915474b3fe3ed7d2a6
+oid sha256:c43950f90e5434aa3343a1dfa434c47c41b526821d2cbe201c064f4de4140237
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a804dd9b4962bc1e7c8e5b51c83ce95f04ab0a366340b47fc4849e7d4ecffd6d
+oid sha256:3a95215f64b02d62fb58ace326ad670f1d16eb1761f7fa3b3478d43d2b8d6108
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2132f43f326e297d8ef25154a9e10a677531d75970aa41267fb256dc43414e
+oid sha256:5db441c623ed8e57ba49826485a6550397a94d7b561781147e7002139a75580b
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa1fe22adce1a7356c1d0d6e91024117a9273f74f672af3e57a58c47a35e32e6
+oid sha256:f5dd06f560614f4bc6d17ac4ff058a5dfc8c4fd4b0f0f0c0a6fe992ec6c1b9a3
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.465,
+  "epoch": 1.4653999999999998,
   "eval_steps": 500,
-  "global_step": 14000,
+  "global_step": 14500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1968,6 +1968,76 @@
       "learning_rate": 1.699563266961643e-05,
       "loss": 1.6123344421386718,
       "step": 14000
+    },
+    {
+      "epoch": 1.0016666666666667,
+      "grad_norm": 1.572548747062683,
+      "learning_rate": 1.6916443776312232e-05,
+      "loss": 1.6946664428710938,
+      "step": 14050
+    },
+    {
+      "epoch": 1.0033333333333334,
+      "grad_norm": 1.4154376983642578,
+      "learning_rate": 1.6837200546618386e-05,
+      "loss": 1.6747663879394532,
+      "step": 14100
+    },
+    {
+      "epoch": 1.005,
+      "grad_norm": 1.5416319370269775,
+      "learning_rate": 1.6757905227295814e-05,
+      "loss": 1.6729904174804688,
+      "step": 14150
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 1.6411312818527222,
+      "learning_rate": 1.6678560066582336e-05,
+      "loss": 1.6301991271972656,
+      "step": 14200
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 1.6199766397476196,
+      "learning_rate": 1.65991673141289e-05,
+      "loss": 1.5882893371582032,
+      "step": 14250
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 1.5008357763290405,
+      "learning_rate": 1.6519729220935818e-05,
+      "loss": 1.6250067138671875,
+      "step": 14300
+    },
+    {
+      "epoch": 1.0116666666666667,
+      "grad_norm": 1.6415075063705444,
+      "learning_rate": 1.6440248039288936e-05,
+      "loss": 1.6562266540527344,
+      "step": 14350
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.5272722244262695,
+      "learning_rate": 1.6360726022695772e-05,
+      "loss": 1.7231492614746093,
+      "step": 14400
+    },
+    {
+      "epoch": 1.015,
+      "grad_norm": 1.362077236175537,
+      "learning_rate": 1.6281165425821623e-05,
+      "loss": 1.7879104614257812,
+      "step": 14450
+    },
+    {
+      "epoch": 2.0004,
+      "grad_norm": 1.7108640670776367,
+      "learning_rate": 1.620156850442564e-05,
+      "loss": 1.7281192016601563,
+      "step": 14500
     }
   ],
   "logging_steps": 50,
@@ -1987,7 +2057,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2463264997381652e+18,
+  "total_flos": 1.2804391427086172e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null