Training in progress, step 175, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:034e187a68a928df60de8335d8df6f9d752c366c792ade88c4c13240c4166357
+oid sha256:0d2486faa614fefac339054a626954e901ed19edcd5c4630e13d6f17fcc4e122
 size 536906096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e325c8d6e17b7311ab280d18a60d02cca13364708dc86af9066b50e60d2b98d3
+oid sha256:a9a202cd852528ab00873ca3f1d4f8e386a8264d607612cae77ab5ffeccc6872
 size 269267284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d1ae586164ef573a6c2ef2af404c49503a0d50cf74be438545d9458602c094
+oid sha256:b2e3bd96c9227f8005659a008a5de4b22b3d54ac87368e34f44e67994ab38530
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:c17c000dd3ad474c8365253b4464489310fed0d13c745556138280174b380deb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6,
+  "epoch": 0.7,
   "eval_steps": 500,
-  "global_step": 150,
+  "global_step": 175,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -907,13 +907,163 @@
       "learning_rate": 0.0002,
       "loss": 0.2957,
       "step": 150
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002,
+      "loss": 0.5856,
+      "step": 151
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002,
+      "loss": 0.5389,
+      "step": 152
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002,
+      "loss": 0.5347,
+      "step": 153
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002,
+      "loss": 0.4574,
+      "step": 154
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002,
+      "loss": 0.5172,
+      "step": 155
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002,
+      "loss": 0.4515,
+      "step": 156
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002,
+      "loss": 0.4383,
+      "step": 157
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002,
+      "loss": 0.5203,
+      "step": 158
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002,
+      "loss": 0.5767,
+      "step": 159
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002,
+      "loss": 0.4975,
+      "step": 160
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002,
+      "loss": 0.4923,
+      "step": 161
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002,
+      "loss": 0.4294,
+      "step": 162
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002,
+      "loss": 0.4449,
+      "step": 163
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 0.4739,
+      "step": 164
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 0.508,
+      "step": 165
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 0.413,
+      "step": 166
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 0.4587,
+      "step": 167
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 0.4465,
+      "step": 168
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002,
+      "loss": 0.4142,
+      "step": 169
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002,
+      "loss": 0.4477,
+      "step": 170
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002,
+      "loss": 0.4854,
+      "step": 171
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002,
+      "loss": 0.4451,
+      "step": 172
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002,
+      "loss": 0.4283,
+      "step": 173
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 0.4031,
+      "step": 174
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 0.395,
+      "step": 175
     }
   ],
   "logging_steps": 1,
   "max_steps": 250,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 1.165066384195584e+16,
+  "total_flos": 1.382556660645888e+16,
   "trial_name": null,
   "trial_params": null
 }