Training in progress, step 105, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8afdd40294379d1dcf8fa826f72105b7ae2a04934f6f3e04c73e44139fd8683c
+oid sha256:d9769b91c0469a97e0c1dfb3eefaf9d734458b7e8b64f2d0033b30307051208c
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c156322d8fd224fc583aa0961d9a3a3d9095c3243790fe54c6712cb71d236ec1
+oid sha256:8c2ebc5d185dff679794f23dcfbb5fa3e43da9d96ae25e9a3de19de0300ceda4
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0944a3edc8124518b8a6cb208c614a99c44e0e66bdc642a03f43a707b184da2c
+oid sha256:b6a076a27efe9310ca2d1126f2fd97f6a436090ae30ab5799eaee441f38e4441
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:981f3fda4f937bab1069c5a15164015d61f2e8dc63af50b10838f184e1a549af
+oid sha256:5618857120fccafc89c96d1c790dffa251460363284f4215ca3298967c397b5f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12940795858945325,
+  "epoch": 0.1358783565189259,
   "eval_steps": 386,
-  "global_step": 100,
+  "global_step": 105,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -715,6 +715,41 @@
       "learning_rate": 9.995751180380466e-05,
       "loss": 0.9644,
       "step": 100
+    },
+    {
+      "epoch": 0.13070203817534778,
+      "grad_norm": 0.9827906489372253,
+      "learning_rate": 9.995579553364887e-05,
+      "loss": 0.9583,
+      "step": 101
+    },
+    {
+      "epoch": 0.13199611776124232,
+      "grad_norm": 1.035618543624878,
+      "learning_rate": 9.995404529817791e-05,
+      "loss": 1.0366,
+      "step": 102
+    },
+    {
+      "epoch": 0.13329019734713685,
+      "grad_norm": 1.2775524854660034,
+      "learning_rate": 9.995226109858178e-05,
+      "loss": 0.9353,
+      "step": 103
+    },
+    {
+      "epoch": 0.13458427693303138,
+      "grad_norm": 1.0101919174194336,
+      "learning_rate": 9.995044293607355e-05,
+      "loss": 0.9045,
+      "step": 104
+    },
+    {
+      "epoch": 0.1358783565189259,
+      "grad_norm": 0.8396942019462585,
+      "learning_rate": 9.994859081188943e-05,
+      "loss": 0.867,
+      "step": 105
     }
   ],
   "logging_steps": 1,
@@ -734,7 +769,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.117937171693568e+17,
+  "total_flos": 1.1738340302782464e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null