Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5abfbc4ca39f5a130360788b6dd8970c52cecc1e11057fba387e8decc03bb7e9
+oid sha256:41f18fc7e74258333a25c19fe47e572895ed879509f4aab2be10b6c2371a867c
 size 662430992

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22abe73ac1ab43770ddb3a259bdfa1c5305600d48036d6a5191cca115dfcb6c9
+oid sha256:8d9de82ecc324921f3649821c7484e3abd1d02702536f88c62390280655beb45
 size 674384884

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cacd830ceec2afd834278f09d2eb0c968694220810253312e53de90e28f63c21
+oid sha256:9ec4f0b141575c4b7ac15ebfa3b42720df95605bb4cc809c8a460a7470c51388
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e507484343820cafb5a65c2e6209bc3fd73610b605668935338da72690bf6d1
+oid sha256:daeac8d9460d1c76c0a28ac63a19ba7e95fb660fc1b7c3b4108934430da5d4ca
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5df6eeb2a23fd11d060f2ffaa6e0de4d9b7f0f0af5bd5bbc1578266e1ab4e099
+oid sha256:1657d041730ea9224af430b9fbaef527276ecff667ca052e9c451df72b149e90
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aa7faa37a30de751af30e38238537f1a13b3ce7bb7ad7580d174db3e1679527
+oid sha256:edffb45adc29f047543eac9059e00848d17f168dc4f70ae160f4d15fee9bddd3
 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": 2.857142857142857,
+  "epoch": 5.714285714285714,
   "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": 289.018,
       "eval_steps_per_second": 3.081,
       "step": 20
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 4.21875,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 4.6968,
+      "step": 30
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 4.3713,
+      "step": 40
+    },
+    {
+      "epoch": 5.714285714285714,
+      "eval_loss": 3.2811784744262695,
+      "eval_runtime": 4.8,
+      "eval_samples_per_second": 312.707,
+      "eval_steps_per_second": 3.333,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7157112027217920.0,
+  "total_flos": 1.431422405443584e+16,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null