Training in progress, step 420, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2bf99fb685178192738cf86432b2684638045005ccd4dad705c36d3b36a73b0
+oid sha256:73933fec6f39ff31db8b4063588eb471127f6937633d45d1c3cc37e646eb1f1a
 size 251748704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96ed3cfef6230556f913bb341659e165d1be11d6a9e849714dac2a66a498d0df
+oid sha256:8c5760d20545fd2a01ca6f9f4c34b708052b116e7c07230cf2bf22840626e187
 size 128585300

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7603b6b83c497176f236a2c73c8a07f344da1a72a0a5ded53652a2f84228ba12
+oid sha256:4e2e8252e83bd5cb5ab2bae1256afc20758f78bcd5fbe5ea0d60fb2a141e1a7d
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f142e3a672235a56cd0672c786ad49159c4e006a26daaaf4b38dc18a1d06f8
+oid sha256:351eb17693dc7c368b46ffc4b9a63a06cd04709ba8be0c043bb013a87b50a082
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc3f301327de19cd057bce0e3ee228e341531645f8ebf0f7b04b52e6473bc6f
+oid sha256:35311861be4c0bd5f63e4e6b59540c760ecd18629f1a0c00f03730317db34397
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a9939c7e7b263164e7af201bc00aa2f1b1bb48da7327f4e5bb0866b6b5b163b
+oid sha256:ce723a195946d3a4ab64decb27f015fa2225e0bf59a73b5ef3fc3b70f932fbcc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f8e14b456d7fc01f5ad21526616d8f86a1c6c40024725332f505f34df4d95a
+oid sha256:d7641dde43bc7a22d17d22ddcaa29ef3541065d43d71357b77f45ce61017cfec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3309859154929577,
+  "epoch": 1.4788732394366197,
   "eval_steps": 42,
-  "global_step": 378,
+  "global_step": 420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -969,6 +969,112 @@
       "eval_samples_per_second": 57.003,
       "eval_steps_per_second": 1.788,
       "step": 378
+    },
+    {
+      "epoch": 1.341549295774648,
+      "grad_norm": 1.704418420791626,
+      "learning_rate": 6.930128404315214e-06,
+      "loss": 0.4565,
+      "step": 381
+    },
+    {
+      "epoch": 1.352112676056338,
+      "grad_norm": 1.593887448310852,
+      "learning_rate": 6.601189685384126e-06,
+      "loss": 0.442,
+      "step": 384
+    },
+    {
+      "epoch": 1.3626760563380282,
+      "grad_norm": 1.6920288801193237,
+      "learning_rate": 6.279057507181796e-06,
+      "loss": 0.4766,
+      "step": 387
+    },
+    {
+      "epoch": 1.3732394366197183,
+      "grad_norm": 1.4904849529266357,
+      "learning_rate": 5.9638510407716394e-06,
+      "loss": 0.4798,
+      "step": 390
+    },
+    {
+      "epoch": 1.3838028169014085,
+      "grad_norm": 1.403585433959961,
+      "learning_rate": 5.655686895087329e-06,
+      "loss": 0.4288,
+      "step": 393
+    },
+    {
+      "epoch": 1.3943661971830985,
+      "grad_norm": 1.7020981311798096,
+      "learning_rate": 5.354679073793942e-06,
+      "loss": 0.4431,
+      "step": 396
+    },
+    {
+      "epoch": 1.4049295774647887,
+      "grad_norm": 1.389512538909912,
+      "learning_rate": 5.060938933112891e-06,
+      "loss": 0.4269,
+      "step": 399
+    },
+    {
+      "epoch": 1.415492957746479,
+      "grad_norm": 1.4572571516036987,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.4362,
+      "step": 402
+    },
+    {
+      "epoch": 1.426056338028169,
+      "grad_norm": 1.386979341506958,
+      "learning_rate": 4.495693635076101e-06,
+      "loss": 0.4528,
+      "step": 405
+    },
+    {
+      "epoch": 1.436619718309859,
+      "grad_norm": 1.5919663906097412,
+      "learning_rate": 4.224397587172402e-06,
+      "loss": 0.4448,
+      "step": 408
+    },
+    {
+      "epoch": 1.4471830985915493,
+      "grad_norm": 1.4099351167678833,
+      "learning_rate": 3.9607873614261715e-06,
+      "loss": 0.4233,
+      "step": 411
+    },
+    {
+      "epoch": 1.4577464788732395,
+      "grad_norm": 1.6724328994750977,
+      "learning_rate": 3.7049604790198976e-06,
+      "loss": 0.4849,
+      "step": 414
+    },
+    {
+      "epoch": 1.4683098591549295,
+      "grad_norm": 1.8909960985183716,
+      "learning_rate": 3.4570115817301243e-06,
+      "loss": 0.4443,
+      "step": 417
+    },
+    {
+      "epoch": 1.4788732394366197,
+      "grad_norm": 1.5311111211776733,
+      "learning_rate": 3.217032396915265e-06,
+      "loss": 0.4651,
+      "step": 420
+    },
+    {
+      "epoch": 1.4788732394366197,
+      "eval_loss": 0.12859447300434113,
+      "eval_runtime": 33.526,
+      "eval_samples_per_second": 57.06,
+      "eval_steps_per_second": 1.79,
+      "step": 420
     }
   ],
   "logging_steps": 3,
@@ -988,7 +1094,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1699126902608364e+18,
+  "total_flos": 3.5221252114009293e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null