Training in progress, step 120, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b37deaf920b8381eae0d06baae22833fc0e96251982c087dec65923b1cd311
+oid sha256:9ff4795709659b5c3133b61a5911ed8d15df15ec87081bc03452e6dd3d41f6cb
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84a836ea05e357969d2a141cccec6cd7ec6671771b2b33afcba2fc08fd5428b6
+oid sha256:f7c7af0b9983056e6c3ec7f55870daa18a8f0c3dcefb530cdf2a339175805a82
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:826f026c2db75df00591e6c8cdcb55abd295cfab875bad1a85bc7c261e4b4cc4
+oid sha256:4f219b5994e6487d5d429e825cd95957075b55e11525fe7b9ac21de5083b4df0
 size 6961290854

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2f73e2ab92ed2314dc8e34e2c9a86c2bd8f2a48f49f9ce7c42ffccc444e0e9b
+oid sha256:8b075c9bbdd17509b8a4b87664da7d045174078d883be66bc10e85931ac95fb4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edab11ab9164a8c1e91fde82983060d22f74114a0388c4e5f7d1919ae5183d3e
+oid sha256:05479e428ccbe2211f5336d623be8fe74728c9d4c28953e30ec37093f34b3f92
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1676d02a11ee5a81cb4b9811d1ee8050a6fd51250ad90acc01ba9a7d1ea1295e
+oid sha256:b3842325ed818fc186d52cb9f7b9a5f21fcf8a160a538fa8e372f687ee3a06a1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:477127038fa627ccd8cc28b1e1e3eafd4f5ab2572d0d466ae60a5f66ea0ea5f6
+oid sha256:4feb182584bf13bf0710623c151ae91fe7c2b2d696a015978fda87ce6d60bca8
 size 15024

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": 2.5,
+  "epoch": 3.0,
   "eval_steps": 20,
-  "global_step": 100,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,28 @@
       "eval_samples_per_second": 105.847,
       "eval_steps_per_second": 5.359,
       "step": 100
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.88671875,
+      "learning_rate": 0.00019043571606975777,
+      "loss": 0.4378,
+      "step": 110
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 0.4412,
+      "step": 120
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.4695043563842773,
+      "eval_runtime": 14.1704,
+      "eval_samples_per_second": 105.925,
+      "eval_steps_per_second": 5.363,
+      "step": 120
     }
   ],
   "logging_steps": 10,
@@ -144,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.14881997586432e+16,
+  "total_flos": 9.774499349764506e+16,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null