Training in progress, step 126, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a479e925ede0c3da3821d664013f8c545b67f4c0210547884d9612a19eef4f
+oid sha256:f5849698230477377bc43d99927ea0b750ff86b3da0cd6f06982ce816ba6dbcd
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27a7e3cd7b75a685cbd36c0f64b79a56218ed9625b7edaae67dc35cc2696380b
+oid sha256:7c427c14ecb51f7b09cfad05ca6b48fae3ca8b3a89561d714f3b547288cbe22e
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab838fbe570b6d415c10780e3a0e3a3e25daa76549fd9a5954f6f1727ad17437
+oid sha256:b4c2513b077ee0a9d0d20b1ed96188cfd8d5c30d65f28f3d6dee11f2dc6d8ca8
 size 14244

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": 0.2736156351791531,
+  "epoch": 0.41042345276872966,
   "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": 23.321,
       "eval_steps_per_second": 5.864,
       "step": 84
+    },
+    {
+      "epoch": 0.28338762214983715,
+      "grad_norm": 2.819925308227539,
+      "learning_rate": 9.40297765928369e-05,
+      "loss": 1.5062,
+      "step": 87
+    },
+    {
+      "epoch": 0.2931596091205212,
+      "grad_norm": 2.894965410232544,
+      "learning_rate": 9.356593520616948e-05,
+      "loss": 1.5876,
+      "step": 90
+    },
+    {
+      "epoch": 0.30293159609120524,
+      "grad_norm": 2.7666544914245605,
+      "learning_rate": 9.308597683653975e-05,
+      "loss": 1.4585,
+      "step": 93
+    },
+    {
+      "epoch": 0.3127035830618892,
+      "grad_norm": 2.8919670581817627,
+      "learning_rate": 9.259007904196023e-05,
+      "loss": 1.5846,
+      "step": 96
+    },
+    {
+      "epoch": 0.32247557003257327,
+      "grad_norm": 2.660968542098999,
+      "learning_rate": 9.207842527714767e-05,
+      "loss": 1.5343,
+      "step": 99
+    },
+    {
+      "epoch": 0.3322475570032573,
+      "grad_norm": 2.652714967727661,
+      "learning_rate": 9.155120482565521e-05,
+      "loss": 1.591,
+      "step": 102
+    },
+    {
+      "epoch": 0.34201954397394135,
+      "grad_norm": 2.7949202060699463,
+      "learning_rate": 9.10086127298478e-05,
+      "loss": 1.4614,
+      "step": 105
+    },
+    {
+      "epoch": 0.3517915309446254,
+      "grad_norm": 2.527437686920166,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.5641,
+      "step": 108
+    },
+    {
+      "epoch": 0.36156351791530944,
+      "grad_norm": 2.352187395095825,
+      "learning_rate": 8.987812213377424e-05,
+      "loss": 1.4186,
+      "step": 111
+    },
+    {
+      "epoch": 0.3713355048859935,
+      "grad_norm": 2.577479124069214,
+      "learning_rate": 8.929064185241213e-05,
+      "loss": 1.4607,
+      "step": 114
+    },
+    {
+      "epoch": 0.3811074918566775,
+      "grad_norm": 2.7002623081207275,
+      "learning_rate": 8.868862620982534e-05,
+      "loss": 1.6182,
+      "step": 117
+    },
+    {
+      "epoch": 0.39087947882736157,
+      "grad_norm": 2.521603584289551,
+      "learning_rate": 8.807229791845673e-05,
+      "loss": 1.4524,
+      "step": 120
+    },
+    {
+      "epoch": 0.4006514657980456,
+      "grad_norm": 2.723996877670288,
+      "learning_rate": 8.744188498563641e-05,
+      "loss": 1.2303,
+      "step": 123
+    },
+    {
+      "epoch": 0.41042345276872966,
+      "grad_norm": 2.888556957244873,
+      "learning_rate": 8.679762062923175e-05,
+      "loss": 1.376,
+      "step": 126
+    },
+    {
+      "epoch": 0.41042345276872966,
+      "eval_loss": 1.5374845266342163,
+      "eval_runtime": 22.1691,
+      "eval_samples_per_second": 23.321,
+      "eval_steps_per_second": 5.864,
+      "step": 126
     }
   ],
   "logging_steps": 3,
@@ -246,7 +352,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.335757030732595e+16,
+  "total_flos": 9.503635546098893e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null