Training in progress, step 175, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0336951ec883d6b5de72b925d727ecd4ca0ac6440aa667a10a1cb852d4a63fae
+oid sha256:1d9ef8895aecefde27b9815938ee8b70b7cb60258c13c343c6f4409007de4b8f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d23e380a2d27ccc3f0d359f7f0c38883537fc47cda2a0ef980473b32d1f6a5a
+oid sha256:19e5799f46aa4ac27c728572da7de1ddb0568e884989194df0340fe82104010e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82e3dacf2b05874132bf6fb4325d351a4ab2ba13cd877561594093394c8a7acc
+oid sha256:350629c8726cd8603e94d6658b9108dc8785e8448290744abeabee7c4b3b48d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:963abeacc51d2fd967b0d854376103780952d47675257465be60a3612cecb103
+oid sha256:416d32fdf638b555a0fc031fb149fd18abaec9c234026f168a4a4bd45704a2a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08313466593312549,
+  "epoch": 0.08557980316645272,
   "eval_steps": 34,
-  "global_step": 170,
+  "global_step": 175,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1245,6 +1245,41 @@
       "eval_samples_per_second": 1.898,
       "eval_steps_per_second": 0.633,
       "step": 170
+    },
+    {
+      "epoch": 0.08362369337979095,
+      "grad_norm": 0.4719301164150238,
+      "learning_rate": 1.4020014855162755e-05,
+      "loss": 1.0868,
+      "step": 171
+    },
+    {
+      "epoch": 0.08411272082645639,
+      "grad_norm": 0.3227783143520355,
+      "learning_rate": 1.3091105369447165e-05,
+      "loss": 0.9113,
+      "step": 172
+    },
+    {
+      "epoch": 0.08460174827312184,
+      "grad_norm": 0.37850451469421387,
+      "learning_rate": 1.2191875191630209e-05,
+      "loss": 1.0702,
+      "step": 173
+    },
+    {
+      "epoch": 0.08509077571978728,
+      "grad_norm": 0.29281488060951233,
+      "learning_rate": 1.1322631407993811e-05,
+      "loss": 0.978,
+      "step": 174
+    },
+    {
+      "epoch": 0.08557980316645272,
+      "grad_norm": 0.2620236277580261,
+      "learning_rate": 1.0483670864493778e-05,
+      "loss": 0.9053,
+      "step": 175
     }
   ],
   "logging_steps": 1,
@@ -1264,7 +1299,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.546222132435354e+17,
+  "total_flos": 7.768169842212864e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null