Training in progress, step 120, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40c2ecd92e57b2e66ca22969473f53cb6e090828806462e132c671e6e2d3f419
+oid sha256:72b290f1c24978d16c820a50cf1ece704d1a3694707e231961893224ec5fcc33
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5b74b9dc7e89f78c99f07af87ab50ab5df7a6480691241092ee5f8486f93d4d
+oid sha256:2394561584b9bdeac1f2473f73aa1da88813b7bdff5f498216e793cf6736fcd8
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddb8fcdae8dea7e10388731f63246ec0494e51d6d509273113166b14d83f0e3
+oid sha256:e5ecc34e614d126f5d7e59e169befe0eebcb7657bb3f2af7aa9c8a5ae429bbb3
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24238ca2ad5e52c7a2d983c253be8a0ab25f258c2785c7ba56c4bfa08fb89d84
+oid sha256:49afa07518bb8f1dc09e650f1ace03ef12ab35ad1dfaa70238845dc06f9efcd5
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d429d3d3635edcf38935f000b0d1f4e5db465042c289fb4623c33dce588231ab
+oid sha256:0b34b977f0b4e5c0c89d8dd446f627fbac9a5e7e945e487b3b1a5a2235e2ee07
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.6923076923076925,
+  "epoch": 9.23076923076923,
   "eval_steps": 40,
-  "global_step": 100,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,28 @@
       "learning_rate": 0.00019264940672148018,
       "loss": 9.998,
       "step": 100
+    },
+    {
+      "epoch": 8.461538461538462,
+      "grad_norm": 0.345703125,
+      "learning_rate": 0.00019043571606975777,
+      "loss": 9.942,
+      "step": 110
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 9.8887,
+      "step": 120
+    },
+    {
+      "epoch": 9.23076923076923,
+      "eval_loss": 9.867681503295898,
+      "eval_runtime": 5.2873,
+      "eval_samples_per_second": 283.888,
+      "eval_steps_per_second": 4.539,
+      "step": 120
     }
   ],
   "logging_steps": 10,
@@ -120,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 40915854950400.0,
+  "total_flos": 49099025940480.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null