Training in progress, step 135, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f4ab89bfd08067012042eb1067028e346fc22d43bcdede78423832cb1b25414
+oid sha256:b53757c450e806fa0582f6da980220020345670b993e63bf8d59758c647ec13e
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:881de5d933722541efaecd471328000119ad52ffaca50c9c1c58ee44dd5dccab
+oid sha256:a62f2d146799cdd29e89bf7d951426b0237e01e6e5606f9b041f19bfe0a9ae8c
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec2dba37f17e925003f4d281a6f44eca5d39774813ad0c3726b50a85b542608e
+oid sha256:70d8ffd5d0306b34d29b48a6526b5741dc24dc3acdbe564b95d57b68075e66c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccb887ab76e166b8621433fbbca8d1978648c385cddb0300477edcffe4035a1a
+oid sha256:e900207fcc2d3955802905e12eea3ef81eb975d535a9ef6fb02c7c84a229aca9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16823034616628924,
+  "epoch": 0.1747007440957619,
   "eval_steps": 386,
-  "global_step": 130,
+  "global_step": 135,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -925,6 +925,41 @@
       "learning_rate": 9.989125425114638e-05,
       "loss": 1.0888,
       "step": 130
+    },
+    {
+      "epoch": 0.16952442575218377,
+      "grad_norm": 0.9069584608078003,
+      "learning_rate": 9.988851963291522e-05,
+      "loss": 0.8579,
+      "step": 131
+    },
+    {
+      "epoch": 0.1708185053380783,
+      "grad_norm": 0.8150789141654968,
+      "learning_rate": 9.988575109511026e-05,
+      "loss": 0.7622,
+      "step": 132
+    },
+    {
+      "epoch": 0.17211258492397283,
+      "grad_norm": 1.0844395160675049,
+      "learning_rate": 9.988294863961387e-05,
+      "loss": 0.9284,
+      "step": 133
+    },
+    {
+      "epoch": 0.17340666450986736,
+      "grad_norm": 1.0463049411773682,
+      "learning_rate": 9.988011226833146e-05,
+      "loss": 0.9185,
+      "step": 134
+    },
+    {
+      "epoch": 0.1747007440957619,
+      "grad_norm": 0.9481234550476074,
+      "learning_rate": 9.987724198319148e-05,
+      "loss": 0.8631,
+      "step": 135
     }
   ],
   "logging_steps": 1,
@@ -944,7 +979,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4533183232016384e+17,
+  "total_flos": 1.5092151817863168e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null