Training in progress, step 1050, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff8c43c5d0a70fdd3c5a092f45b576ce4d6695039dd5efa0b3372bf9de2b4bc
+oid sha256:a0e95a395e4b276d4c7eacb38473e906143acd581ad5443468b2f990e935ddfa
 size 1302756720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f88ef668a708a27bef57939446f0bd0a3ccfb9b33174df84a17271afc84ba685
+oid sha256:6a2654c6ae5ddd64e2c312c0b2a422dfd011eb63a7c92d74501c71b32ea30675
 size 2565803322

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4252aa9c1b46b4624b57d2f922441631bdb1287ae4a706e82d33f1ad66a031db
+oid sha256:425026aaf9fa84dc0943287ca090b73e61643088d53bfd5fc139a1654ad51203
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60a827078c85f0fd366049a88039c9056197c970413749f5c2cbfe85bd3bd7d6
+oid sha256:9cf334b45c59ec3117af6235b0cb6b8da2aab8bbc78c388edc1a1925c6731983
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.324646234512329,
   "best_model_checkpoint": "./output/checkpoint-150",
-  "epoch": 0.027973766823112547,
+  "epoch": 0.03263606129363131,
   "eval_steps": 150,
-  "global_step": 900,
+  "global_step": 1050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -685,6 +685,119 @@
       "eval_samples_per_second": 11.895,
       "eval_steps_per_second": 11.895,
       "step": 900
+    },
+    {
+      "epoch": 0.028284586454480464,
+      "grad_norm": 29.72920036315918,
+      "learning_rate": 9.340773121260896e-05,
+      "loss": 1.1198,
+      "step": 910
+    },
+    {
+      "epoch": 0.02859540608584838,
+      "grad_norm": 26.55568504333496,
+      "learning_rate": 9.32477428972347e-05,
+      "loss": 1.206,
+      "step": 920
+    },
+    {
+      "epoch": 0.0289062257172163,
+      "grad_norm": 17.740917205810547,
+      "learning_rate": 9.308597683653978e-05,
+      "loss": 1.2149,
+      "step": 930
+    },
+    {
+      "epoch": 0.029217045348584218,
+      "grad_norm": 16.225730895996094,
+      "learning_rate": 9.292243968009333e-05,
+      "loss": 1.1254,
+      "step": 940
+    },
+    {
+      "epoch": 0.029527864979952134,
+      "grad_norm": 29.286996841430664,
+      "learning_rate": 9.275713815026734e-05,
+      "loss": 1.3235,
+      "step": 950
+    },
+    {
+      "epoch": 0.02983868461132005,
+      "grad_norm": 22.0376033782959,
+      "learning_rate": 9.259007904196024e-05,
+      "loss": 1.4885,
+      "step": 960
+    },
+    {
+      "epoch": 0.030149504242687968,
+      "grad_norm": 26.638015747070312,
+      "learning_rate": 9.242126922231766e-05,
+      "loss": 1.2483,
+      "step": 970
+    },
+    {
+      "epoch": 0.030460323874055884,
+      "grad_norm": 12.953681945800781,
+      "learning_rate": 9.225071563045009e-05,
+      "loss": 1.5445,
+      "step": 980
+    },
+    {
+      "epoch": 0.0307711435054238,
+      "grad_norm": 19.948116302490234,
+      "learning_rate": 9.207842527714768e-05,
+      "loss": 1.2768,
+      "step": 990
+    },
+    {
+      "epoch": 0.03108196313679172,
+      "grad_norm": 16.087295532226562,
+      "learning_rate": 9.190440524459205e-05,
+      "loss": 1.0367,
+      "step": 1000
+    },
+    {
+      "epoch": 0.031392782768159634,
+      "grad_norm": 20.46804428100586,
+      "learning_rate": 9.172866268606516e-05,
+      "loss": 1.1743,
+      "step": 1010
+    },
+    {
+      "epoch": 0.031703602399527554,
+      "grad_norm": 10.569546699523926,
+      "learning_rate": 9.155120482565522e-05,
+      "loss": 1.2312,
+      "step": 1020
+    },
+    {
+      "epoch": 0.032014422030895474,
+      "grad_norm": 23.994094848632812,
+      "learning_rate": 9.137203895795986e-05,
+      "loss": 1.2055,
+      "step": 1030
+    },
+    {
+      "epoch": 0.03232524166226339,
+      "grad_norm": 18.373334884643555,
+      "learning_rate": 9.11911724477861e-05,
+      "loss": 1.4074,
+      "step": 1040
+    },
+    {
+      "epoch": 0.03263606129363131,
+      "grad_norm": 18.44525718688965,
+      "learning_rate": 9.100861272984782e-05,
+      "loss": 1.1465,
+      "step": 1050
+    },
+    {
+      "epoch": 0.03263606129363131,
+      "eval_loss": 1.3763073682785034,
+      "eval_runtime": 44.4721,
+      "eval_samples_per_second": 11.243,
+      "eval_steps_per_second": 11.243,
+      "step": 1050
     }
   ],
   "logging_steps": 10,
@@ -704,7 +817,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.218529161795584e+16,
+  "total_flos": 9.590225761995571e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null