Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc3e671a65038f4899a55dec4cfd97e67a440d971093fbf09b12471fda37cedb
+oid sha256:0af0e3452e1dd4f2872d97862892d5f7780935c9cca688534e4358ecd6f913a9
 size 28130688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe762fd4e86adc0ca4e1d9002b17ab5ca3657d0af542c8db9631539f774ffedc
+oid sha256:6d48098e754298a2a5e4f2d3490d1a8344bad1094a06f57f4db1a43e07de618f
 size 28684730

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02bd6697dd0ac01f79967d93e880e93c5ad7e5d6a672668dd596f9f42c435066
+oid sha256:b9d8ba6dc294a7802a4dafc0e564c1a2eee3305104ad939fbc56d5ce507ea444
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1946c0d35865c02655624537450071d8e3a581f1d24f3c539357cae293b3d2d2
+oid sha256:1f0cceb0ed85b2c6f37fd08e1761f95ce6ce00ab47aa275d076d6aa53a386d4e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9faf933c304288a566e09316737d2bdccb42e76da4138d98110982bcbf5dbf1
+oid sha256:c2204e8c1dd9dc7722a4f81e5fd4492d8dfa53c90fc9556f23dafd200a539a7a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f2cb6de5c0f2b78c1515e90a9ab03144587d336dd27fc87023f09785c5d64cb
+oid sha256:9003a850e509d15b02ef8ebe5e4de4ee92eba098365621434af147786d9f58d1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f22729b765b6841bd185712dd3ab8bf338866cd8396b5dce62f9950913691a
+oid sha256:02fba4d221acb6fea331334b3de1974a87e216e52fc96554556bafda3bca4247
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.3333333333333335,
+  "epoch": 6.666666666666667,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 296.845,
       "eval_steps_per_second": 2.373,
       "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 48.5,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 9.9786,
+      "step": 30
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 77.5,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 9.7292,
+      "step": 40
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 8.797822952270508,
+      "eval_runtime": 4.9683,
+      "eval_samples_per_second": 302.115,
+      "eval_steps_per_second": 2.415,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 234160803282944.0,
+  "total_flos": 468415307317248.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null