Training in progress, step 2770, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3059fc7ddeb7b2fd3ebfe75095a56e7c15b75f77c4d16dd4acba6368b73bd8b
+oid sha256:5093ae80e82d9ac5ef8471495bb6661a656ff25287d223ed083ad76691dfca25
 size 286855468

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a20bbab186ab5cc252fda554693fc994faa1af559201d0196ab3787104b73fa8
+oid sha256:6247fc8dc13230d787ebaf57f7a9635aaf3e2b8cb4d4c66a2312446f331468ba
 size 573434490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0bcde413360f86077dfdc8d752eff107536b592ff18aefadf4b94dff1de80f5
+oid sha256:b2862b45692129eaef0f58666fa07a85c2812a54e6dd9aa3a383f9edf87f875a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591e137b4025dc158ceb4aa479fcc3dee190f1fba91b8aab023f994b419d6e79
+oid sha256:f72d76e2923f6040c19e77169f2c20b5bbfbf48a4e6f0f782c50393a92864545
 size 1064

last-checkpoint/trainer_state.json

@@ -1,13 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001248067229221414,
+  "epoch": 0.01920636791635176,
   "eval_steps": 500,
-  "global_step": 180,
+  "global_step": 2770,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [],
+  "log_history": [
+    {
+      "epoch": 0.003466853414503928,
+      "grad_norm": 1.0329110622406006,
+      "learning_rate": 1.997688764390331e-05,
+      "loss": 0.5561,
+      "step": 500
+    },
+    {
+      "epoch": 0.006933706829007856,
+      "grad_norm": 1.2828088998794556,
+      "learning_rate": 1.9953775287806617e-05,
+      "loss": 0.5185,
+      "step": 1000
+    },
+    {
+      "epoch": 0.010400560243511783,
+      "grad_norm": 1.9677228927612305,
+      "learning_rate": 1.9930662931709924e-05,
+      "loss": 0.5365,
+      "step": 1500
+    },
+    {
+      "epoch": 0.013867413658015712,
+      "grad_norm": 0.9762986302375793,
+      "learning_rate": 1.990755057561323e-05,
+      "loss": 0.5431,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01733426707251964,
+      "grad_norm": 1.915410041809082,
+      "learning_rate": 1.9884438219516536e-05,
+      "loss": 0.5247,
+      "step": 2500
+    }
+  ],
   "logging_steps": 500,
   "max_steps": 432669,
   "num_input_tokens_seen": 0,
@@ -25,7 +61,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 97627290992640.0,
+  "total_flos": 1502375533608960.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c03c661eb56e3b7d4c1e5e0f4175f735ea4e737bf79b88e68e0d702f8c2446
+oid sha256:79a6919c060dd52ed57f848df248bc4aabdce62edbefb0a48fd6951b2a6895ed
 size 5240