Training in progress, step 126, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6294a9c9e421f26623f265d84c6b0618f883b9dd25deaca3c936e180cf07b24a
+oid sha256:0020ebc06166cd6fbb21fea648ebd8e089cf08d59f8a369d5ccc62994306af35
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e409bc2980559f98a0af9f1edbb4380dbf4021ebd0edbd6c8b2fb477f751ac94
+oid sha256:7f1b4d8adfadaaf59c2e6e469ab5468b025cbbff070f473a59804411605a3047
 size 197158

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f286750a54eebdcf9549d6f63e6795fc731915bf6f7bf2b726b55b05f3f518
+oid sha256:5504ef09e4cfb51812fd7a9abcfb2f28e7b4cf5622051aa506c80b1903c2ce18
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02fd229e57eac985f512ac99036360caf9e39dc610ee15dd6c9283a1b6c69b19
+oid sha256:6628ebff94c3a6b8fdb16ed899453e0564fb950e7ae1d3e33c819c9bdd72e3c4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db29deadf6ae74444d5e6208837d81f47dde9b75671d98526f2bf5be704e381
+oid sha256:4477dcc6fa149a821c6a1471f47125572228d5c13a485cbcd42df776c95bcb70
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840bfe1128fcfee1e64ffedd09794dc200894ff330da30892753d28eb72056a6
+oid sha256:15b25e19ffd8a56430878e7874bc350fc05f2b592464eeaef1dac5822dbb0979
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df224011d0e75c4a97901f6c1b2930bba4bc3a9aa7c877e6c91e796bec6013f
+oid sha256:e00328545513b592b6bf311a002e087bb048e374276594cf37ee8782d28887fc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2194644023514043,
+  "epoch": 0.32919660352710645,
   "eval_steps": 42,
-  "global_step": 84,
+  "global_step": 126,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -227,6 +227,112 @@
       "eval_samples_per_second": 779.15,
       "eval_steps_per_second": 24.481,
       "step": 84
+    },
+    {
+      "epoch": 0.22730241672109733,
+      "grad_norm": 0.017396893352270126,
+      "learning_rate": 9.40297765928369e-05,
+      "loss": 11.92,
+      "step": 87
+    },
+    {
+      "epoch": 0.23514043109079033,
+      "grad_norm": 0.01054318156093359,
+      "learning_rate": 9.356593520616948e-05,
+      "loss": 11.9203,
+      "step": 90
+    },
+    {
+      "epoch": 0.24297844546048333,
+      "grad_norm": 0.016479285433888435,
+      "learning_rate": 9.308597683653975e-05,
+      "loss": 11.9206,
+      "step": 93
+    },
+    {
+      "epoch": 0.25081645983017636,
+      "grad_norm": 0.01747283898293972,
+      "learning_rate": 9.259007904196023e-05,
+      "loss": 11.9208,
+      "step": 96
+    },
+    {
+      "epoch": 0.25865447419986937,
+      "grad_norm": 0.016894422471523285,
+      "learning_rate": 9.207842527714767e-05,
+      "loss": 11.9204,
+      "step": 99
+    },
+    {
+      "epoch": 0.26649248856956237,
+      "grad_norm": 0.015183241106569767,
+      "learning_rate": 9.155120482565521e-05,
+      "loss": 11.9209,
+      "step": 102
+    },
+    {
+      "epoch": 0.27433050293925537,
+      "grad_norm": 0.014355632476508617,
+      "learning_rate": 9.10086127298478e-05,
+      "loss": 11.9201,
+      "step": 105
+    },
+    {
+      "epoch": 0.2821685173089484,
+      "grad_norm": 0.022136807441711426,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9204,
+      "step": 108
+    },
+    {
+      "epoch": 0.29000653167864143,
+      "grad_norm": 0.02453417330980301,
+      "learning_rate": 8.987812213377424e-05,
+      "loss": 11.9206,
+      "step": 111
+    },
+    {
+      "epoch": 0.29784454604833444,
+      "grad_norm": 0.022463472560048103,
+      "learning_rate": 8.929064185241213e-05,
+      "loss": 11.9194,
+      "step": 114
+    },
+    {
+      "epoch": 0.30568256041802744,
+      "grad_norm": 0.020201250910758972,
+      "learning_rate": 8.868862620982534e-05,
+      "loss": 11.9192,
+      "step": 117
+    },
+    {
+      "epoch": 0.31352057478772044,
+      "grad_norm": 0.023930294439196587,
+      "learning_rate": 8.807229791845673e-05,
+      "loss": 11.92,
+      "step": 120
+    },
+    {
+      "epoch": 0.32135858915741344,
+      "grad_norm": 0.01951843872666359,
+      "learning_rate": 8.744188498563641e-05,
+      "loss": 11.9196,
+      "step": 123
+    },
+    {
+      "epoch": 0.32919660352710645,
+      "grad_norm": 0.013068539090454578,
+      "learning_rate": 8.679762062923175e-05,
+      "loss": 11.9193,
+      "step": 126
+    },
+    {
+      "epoch": 0.32919660352710645,
+      "eval_loss": 11.919238090515137,
+      "eval_runtime": 3.3246,
+      "eval_samples_per_second": 775.442,
+      "eval_steps_per_second": 24.364,
+      "step": 126
     }
   ],
   "logging_steps": 3,
@@ -246,7 +352,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1619798261760.0,
+  "total_flos": 2430902599680.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null