Training in progress, step 140, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b290f1c24978d16c820a50cf1ece704d1a3694707e231961893224ec5fcc33
+oid sha256:d94e2e3075b4d29e46e5c0b523fa0341f1cfc942214350c627669d578aadac68
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2394561584b9bdeac1f2473f73aa1da88813b7bdff5f498216e793cf6736fcd8
+oid sha256:b3972db052ecd4c3f09e208a35dde53cb98f3e8470c87ce17ce263b679cb5575
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ecc34e614d126f5d7e59e169befe0eebcb7657bb3f2af7aa9c8a5ae429bbb3
+oid sha256:d12ad40cafcf41ebef3793f1bacea211194d01b1709039dcecfc310b37cfe4c8
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49afa07518bb8f1dc09e650f1ace03ef12ab35ad1dfaa70238845dc06f9efcd5
+oid sha256:2346f71e8fa54bb462ec3536dd3b00a5d7baa51d353b2a407f22bc20619f73ed
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b34b977f0b4e5c0c89d8dd446f627fbac9a5e7e945e487b3b1a5a2235e2ee07
+oid sha256:648d534e3bfa3788d45747301f1f48cbd9086fc244a9af1c996a30c275d122dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.23076923076923,
+  "epoch": 10.76923076923077,
   "eval_steps": 40,
-  "global_step": 120,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,6 +123,20 @@
       "eval_samples_per_second": 283.888,
       "eval_steps_per_second": 4.539,
       "step": 120
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00018519194088383273,
+      "loss": 9.836,
+      "step": 130
+    },
+    {
+      "epoch": 10.76923076923077,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.0001821777815225245,
+      "loss": 9.7845,
+      "step": 140
     }
   ],
   "logging_steps": 10,
@@ -142,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 49099025940480.0,
+  "total_flos": 57282196930560.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null