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:d1dc325e6b55600821a56310ebf67662222694a652b5b968b82eb7e2a6bde4bb
+oid sha256:3c15a34ec1b4d3d4fbaeb960fd708de5db3f303c2b549df51725295172d1360c
 size 4972163696

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9273fd263dab2820280dba2b12410f2f0ceeca554793c563a6c5c8d7630a0d14
+oid sha256:e7544d672f19439e82165eb8bf76e30fd101a87ec3778efd94e86e2741d0051f
 size 2669366920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:766cdc20cd1d2b6d4ec93f9dbaec052b2c9f875210752f86bf41439582618426
+oid sha256:2590f9284e12a5bae29178a457254993014e58377b152f8d15234dfd81a13f59
 size 7762295162

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2667eee8d875561f6539074432e0dd0e4895799b436b03ff4f88447a79b23c54
+oid sha256:f105b50093489fd740a8f6602ddfe873d388d5a0db4242d627bbb8ba93713d73
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f453d97040b5753e846b52c3f3f2ec936ae564e3d843c2334ebea047a9d227d
+oid sha256:9ac67ce68566e593180659981e408823cfcf7642579fefd1cbac723e565bb9c8
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aefbcebbcca874264bb329f31301bfa219bc90bffbd18b02b072517f20157778
+oid sha256:7b138c732cb9c881cb2fed2b16c2fccdaaf3f697d85bd2ae2853572bd36b881f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4716981132075472,
+  "epoch": 0.9433962264150944,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 40.276,
       "eval_steps_per_second": 5.045,
       "step": 50
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 1.6412,
+      "step": 60
+    },
+    {
+      "epoch": 0.660377358490566,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.0001999919114627769,
+      "loss": 1.6797,
+      "step": 70
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.94140625,
+      "learning_rate": 0.00019992721101571236,
+      "loss": 1.7777,
+      "step": 80
+    },
+    {
+      "epoch": 0.8490566037735849,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00019979785198644806,
+      "loss": 1.7622,
+      "step": 90
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 1.5078125,
+      "learning_rate": 0.00019960391807762463,
+      "loss": 1.7494,
+      "step": 100
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "eval_loss": 1.6423826217651367,
+      "eval_runtime": 38.0472,
+      "eval_samples_per_second": 39.451,
+      "eval_steps_per_second": 4.941,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.82964197523456e+16,
+  "total_flos": 3.65928395046912e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null