Training in progress, step 100, checkpoint

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb038a9aa92fa45d9aaabd2236e3c7d97215a54e110c0afb98849299578118c
+oid sha256:ab3c6c30be30d002c9bdb888b5b51dcd1032f1ed3600ae01f1dd544de2e99f52
 size 4943178720

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4aae276a4d8f9fb822a9e4f697b67666e3e5d61fe21cb70d7431d9eafd2583
+oid sha256:90b7deaad79314a2043c763969d6a803e98dc491daa862efa58a7f54a22f4410
 size 4999819336

last-checkpoint/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a23643415bc9ed079fe90713e52ecaf079f5939f7f91d82a4b54b3db2d10ac
+oid sha256:4274c40f1493eb14129f4621c74c1fabcbc7e4e381228bc6a5f4cdee5547cdd5
 size 4540532728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16332399f14451488556d919f5130e1ff3869a46bdf298eef702a40ecdcaefd7
+oid sha256:0f2ddc52625275a965f3a109531a19102ed2af5bf842fd054c81e4317fd46f90
 size 14710155092

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455445cc351d1d9c0932fce6221afb99c553d40bbefe6e459ef4b63ef6e54132
+oid sha256:9420ac59722557c2d75561b7a80141668226ad32b0226580eab59c780161b06f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3353489b38799fd56e115bb7a4e2a7a61242a09d303dca9e218c08878b9b8728
+oid sha256:aeada689887050f844873eed093c0e42e31037d558c794e13e2aaf05bbc18b5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11848341232227488,
+  "epoch": 0.23696682464454977,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 13.643,
       "eval_steps_per_second": 6.826,
       "step": 50
+    },
+    {
+      "epoch": 0.14218009478672985,
+      "grad_norm": 88.0,
+      "learning_rate": 9.6e-05,
+      "loss": 3.0907,
+      "step": 60
+    },
+    {
+      "epoch": 0.16587677725118483,
+      "grad_norm": 54.25,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 3.2869,
+      "step": 70
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 75.5,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 3.5309,
+      "step": 80
+    },
+    {
+      "epoch": 0.2132701421800948,
+      "grad_norm": 72.5,
+      "learning_rate": 0.000144,
+      "loss": 3.6509,
+      "step": 90
+    },
+    {
+      "epoch": 0.23696682464454977,
+      "grad_norm": 70.0,
+      "learning_rate": 0.00016,
+      "loss": 3.7776,
+      "step": 100
+    },
+    {
+      "epoch": 0.23696682464454977,
+      "eval_loss": 3.771571636199951,
+      "eval_runtime": 110.614,
+      "eval_samples_per_second": 13.57,
+      "eval_steps_per_second": 6.789,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8737589192294400.0,
+  "total_flos": 1.74751783845888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null