Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:385c6700aae0cc7ebcd189dac2c66ebfc53f7fec408316a5242d59c2e3c9f07e
+oid sha256:0130799898020a53b14cabd263a81e22f27ec0696f688e0cd14317bbc408dba0
 size 349243752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b7cd9825c01711620bb5dcc0b9e19811d636fc9094641303dd9fc13e79fedc
+oid sha256:af84095ea6d9f6f4e13aeeea1737265b67d0775777ae4ab57423d3ed644c4081
 size 177909253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a273191378e295e79d8e7b721ac898d977266d9fc45a22812d9173affa953415
+oid sha256:4944f7f3f8d9cc24a998faf94675bbb1d591022b8f0394f9e1700a104dca058b
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:524fe1b39d0e74a74202e97fd363b331b733ce7e41558e0e4b19a0ac27092713
+oid sha256:8f89c09364acfd91102561379138b88af0a420d76fde4e419b7a16abec655975
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a73aacd895d114c25edf917acb63200c1b0df74b52c8f0b257b638ca866429
+oid sha256:dda3a1cdc480778259cfeb010764235ae8da3862f43cb398867dec097dc012ae
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9333333333333336,
+  "epoch": 3.2,
   "eval_steps": 500,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -778,6 +778,76 @@
       "learning_rate": 1.7102549540480392e-05,
       "loss": 1.1838,
       "step": 1100
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.2694341838359833,
+      "learning_rate": 1.706160768693108e-05,
+      "loss": 1.1659,
+      "step": 1110
+    },
+    {
+      "epoch": 2.986666666666667,
+      "grad_norm": 0.21248756349086761,
+      "learning_rate": 1.7020278943499707e-05,
+      "loss": 1.1724,
+      "step": 1120
+    },
+    {
+      "epoch": 3.013333333333333,
+      "grad_norm": 0.2432037740945816,
+      "learning_rate": 1.6978565424772645e-05,
+      "loss": 1.1635,
+      "step": 1130
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.23135386407375336,
+      "learning_rate": 1.693646926502333e-05,
+      "loss": 1.2128,
+      "step": 1140
+    },
+    {
+      "epoch": 3.066666666666667,
+      "grad_norm": 0.24014094471931458,
+      "learning_rate": 1.6893992618103017e-05,
+      "loss": 1.1835,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0933333333333333,
+      "grad_norm": 0.24849995970726013,
+      "learning_rate": 1.6851137657330615e-05,
+      "loss": 1.1567,
+      "step": 1160
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 0.2538585364818573,
+      "learning_rate": 1.6807906575381463e-05,
+      "loss": 1.1868,
+      "step": 1170
+    },
+    {
+      "epoch": 3.1466666666666665,
+      "grad_norm": 0.24177521467208862,
+      "learning_rate": 1.6764301584175155e-05,
+      "loss": 1.1521,
+      "step": 1180
+    },
+    {
+      "epoch": 3.1733333333333333,
+      "grad_norm": 0.2552991807460785,
+      "learning_rate": 1.672032491476236e-05,
+      "loss": 1.1725,
+      "step": 1190
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.23876914381980896,
+      "learning_rate": 1.667597881721068e-05,
+      "loss": 1.1542,
+      "step": 1200
     }
   ],
   "logging_steps": 10,
@@ -797,7 +867,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5952939212425134e+18,
+  "total_flos": 1.740213740302762e+18,
   "train_batch_size": 36,
   "trial_name": null,
   "trial_params": null