Training in progress, step 168, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aadd79cb0ce90a3800ba84eddb5d6ed311601f6907fd8577721c4a48d11c900a
+oid sha256:7a2a60feb1e96d790294c0b5eae9acc5fb705f4771269491fe8bf9cd16a835e5
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3369db71b47a6b28d8af870490f2fffae251fdfc9b2ec04d614352e035cb1c3a
+oid sha256:7cbcfaf89e28391d7c82167b07cd38f9662d61b8bf262f3ab44b55dd4fde9bc5
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e19d88c5ee8945747e0c8f00ae8f30f12218b1bee6b5d59ad749865193f9388
+oid sha256:98eb662dc5bc7d04a24c041329941502e3aed4d1fcb64bac57ca17d20f66e522
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00328545513b592b6bf311a002e087bb048e374276594cf37ee8782d28887fc
+oid sha256:2f516a6e4e8a8eba956b80cb2ea416b9fd98f0dec12d7d9d9a36274d0eef4a63
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02641232575201761,
+  "epoch": 0.03521643433602348,
   "eval_steps": 42,
-  "global_step": 126,
+  "global_step": 168,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -333,6 +333,112 @@
       "eval_samples_per_second": 48.682,
       "eval_steps_per_second": 6.089,
       "step": 126
+    },
+    {
+      "epoch": 0.02704119065087517,
+      "grad_norm": 0.3487012982368469,
+      "learning_rate": 8.613974319136958e-05,
+      "loss": 1.1212,
+      "step": 129
+    },
+    {
+      "epoch": 0.027670055549732734,
+      "grad_norm": 0.37176796793937683,
+      "learning_rate": 8.54684960502629e-05,
+      "loss": 1.0707,
+      "step": 132
+    },
+    {
+      "epoch": 0.028298920448590295,
+      "grad_norm": 0.3854920268058777,
+      "learning_rate": 8.478412753017433e-05,
+      "loss": 1.1204,
+      "step": 135
+    },
+    {
+      "epoch": 0.028927785347447856,
+      "grad_norm": 0.3561486303806305,
+      "learning_rate": 8.408689080954998e-05,
+      "loss": 1.1238,
+      "step": 138
+    },
+    {
+      "epoch": 0.029556650246305417,
+      "grad_norm": 0.35637167096138,
+      "learning_rate": 8.33770438273574e-05,
+      "loss": 1.1415,
+      "step": 141
+    },
+    {
+      "epoch": 0.030185515145162982,
+      "grad_norm": 0.37608301639556885,
+      "learning_rate": 8.265484918766243e-05,
+      "loss": 1.1374,
+      "step": 144
+    },
+    {
+      "epoch": 0.030814380044020543,
+      "grad_norm": 0.3702179789543152,
+      "learning_rate": 8.192057406248028e-05,
+      "loss": 1.1001,
+      "step": 147
+    },
+    {
+      "epoch": 0.031443244942878104,
+      "grad_norm": 0.35054582357406616,
+      "learning_rate": 8.117449009293668e-05,
+      "loss": 1.122,
+      "step": 150
+    },
+    {
+      "epoch": 0.03207210984173567,
+      "grad_norm": 0.35157763957977295,
+      "learning_rate": 8.041687328877567e-05,
+      "loss": 1.1126,
+      "step": 153
+    },
+    {
+      "epoch": 0.032700974740593226,
+      "grad_norm": 0.3567587435245514,
+      "learning_rate": 7.964800392625129e-05,
+      "loss": 1.1196,
+      "step": 156
+    },
+    {
+      "epoch": 0.03332983963945079,
+      "grad_norm": 0.33376169204711914,
+      "learning_rate": 7.886816644444098e-05,
+      "loss": 1.1269,
+      "step": 159
+    },
+    {
+      "epoch": 0.033958704538308356,
+      "grad_norm": 0.33005964756011963,
+      "learning_rate": 7.807764934001874e-05,
+      "loss": 1.0881,
+      "step": 162
+    },
+    {
+      "epoch": 0.03458756943716591,
+      "grad_norm": 0.3465365171432495,
+      "learning_rate": 7.727674506052743e-05,
+      "loss": 1.0912,
+      "step": 165
+    },
+    {
+      "epoch": 0.03521643433602348,
+      "grad_norm": 0.3523496985435486,
+      "learning_rate": 7.646574989618938e-05,
+      "loss": 1.0962,
+      "step": 168
+    },
+    {
+      "epoch": 0.03521643433602348,
+      "eval_loss": 1.1077728271484375,
+      "eval_runtime": 165.0063,
+      "eval_samples_per_second": 48.695,
+      "eval_steps_per_second": 6.091,
+      "step": 168
     }
   ],
   "logging_steps": 3,
@@ -352,7 +458,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.687766294115123e+16,
+  "total_flos": 3.5836883921534976e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null