Training in progress, step 100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08e681e5ea6b3f9d1967cfb921e4181468c024c2e5156dc16e168c34ee55c76c
+oid sha256:45756bb5ceecd3f0ffe743739575b8657d30adecb0a073a83fa4b22fcee881ab
 size 4972163696

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074bd67ba7926a399920b42f5f69ba32603bbdc8b3c66d1145a9993914871ae7
+oid sha256:aae46d4535947a904fc5f007b34b6f78afa9077f426d9d252332b79408c50959
 size 2669366920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f387506b03a99b2a3f2552ff575a749d83fe42fb942c0e8f32eea8f4f8e05b6
+oid sha256:afd5ba679ccea1a882cb85ba3b4eefb198e3bb6daed7c5fe6c55de9f0ce017b7
 size 7762295162

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f845cccc365f42082caa7da8e604f0c659004980fe3b3663dcc7e14c2ca04bce
+oid sha256:83ff1a6f801ea96ddc1232f1cdbee583664fcf8d4ca09f9f36e0e9551ee5065a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc2365c0dcf059a80feab8740ee48b0ab99d23a36a4fcdd0867be4b5ceb6e9e
+oid sha256:1b6abbd295103d5a526850424c4a7bb49c9d406bb8723466f4b22751971a77b8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dfa48462bc67143df2cd639a35fe858a2249d5fc29a8dbef955d03c6c86c4f8
+oid sha256:b67cc672a22fc2c18259828e1cd5463343d22afb42bc6c37ae675bd2bf95e74b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b88a2d1f28d47a4c4e8ea38eec6b15121f358a10dad34451756b36840a679ec
+oid sha256:cd4bcaf2d11c8c4d769507d61ddf4487c470739ecf49e91238571119fd0be945
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5258a10d326b43bb322f9f7412c08a5d462c4dd53d2018b15d95caea3824d34f
+oid sha256:d429d3d3635edcf38935f000b0d1f4e5db465042c289fb4623c33dce588231ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.509433962264151,
+  "epoch": 1.8867924528301887,
   "eval_steps": 20,
-  "global_step": 80,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,28 @@
       "eval_samples_per_second": 53.192,
       "eval_steps_per_second": 3.331,
       "step": 80
+    },
+    {
+      "epoch": 1.6981132075471699,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.00019458172417006347,
+      "loss": 1.0807,
+      "step": 90
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "grad_norm": 0.80859375,
+      "learning_rate": 0.00019264940672148018,
+      "loss": 1.3163,
+      "step": 100
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "eval_loss": 1.7708204984664917,
+      "eval_runtime": 19.9313,
+      "eval_samples_per_second": 75.309,
+      "eval_steps_per_second": 4.716,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -122,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.850280234267443e+16,
+  "total_flos": 7.313993814455091e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null