Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40d5693affa8c3c7b723c5daf60ed0b746f97958aee56ec5b5ea1f3ad326b755
+oid sha256:b7aa8a98b6e70791a74e60e208c3ac40c8361199195dd54e893d808393c784d3
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6de35a1438d91fac87e649ba5c3d5a90121e6ce3ca86df298c35f641323d5759
+oid sha256:04c7916ae0a42a86555408ab18196278c14a6105644f0d14991b727630eb3e96
 size 63350356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a14f694512fc40766d9fafd579c27dac8ba7e3555b949d256edd6441aadd30ee
+oid sha256:bd7553ed48fb9af9185475a0992950d3f88e91369c31402fc9b619ffc0bfb053
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c2ffac78fadf1567b17338549b0e2194f2cf0e411216d20570b3e79a5739ee
+oid sha256:30f8e86cd65221b2d68c30f7fa44bf055b87fd8f319383787431dfc91b0128d9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01,
+  "epoch": 0.018,
   "eval_steps": 1000,
-  "global_step": 25,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,13 +157,133 @@
       "learning_rate": 0.00015463917525773197,
       "loss": 1.6624,
       "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00015257731958762886,
+      "loss": 1.95,
+      "step": 26
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00015051546391752578,
+      "loss": 1.5541,
+      "step": 27
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001484536082474227,
+      "loss": 1.4851,
+      "step": 28
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014639175257731958,
+      "loss": 1.6751,
+      "step": 29
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001443298969072165,
+      "loss": 1.5637,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014226804123711342,
+      "loss": 1.6947,
+      "step": 31
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001402061855670103,
+      "loss": 1.363,
+      "step": 32
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013814432989690722,
+      "loss": 2.0642,
+      "step": 33
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013608247422680414,
+      "loss": 1.5458,
+      "step": 34
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013402061855670103,
+      "loss": 1.8339,
+      "step": 35
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013195876288659794,
+      "loss": 1.6049,
+      "step": 36
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00012989690721649486,
+      "loss": 1.5555,
+      "step": 37
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012783505154639175,
+      "loss": 1.5485,
+      "step": 38
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012577319587628866,
+      "loss": 2.0987,
+      "step": 39
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012371134020618558,
+      "loss": 1.4402,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012164948453608247,
+      "loss": 1.4069,
+      "step": 41
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00011958762886597938,
+      "loss": 1.5902,
+      "step": 42
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001175257731958763,
+      "loss": 1.8907,
+      "step": 43
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00011546391752577319,
+      "loss": 1.6717,
+      "step": 44
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001134020618556701,
+      "loss": 1.8157,
+      "step": 45
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 3557655141089280.0,
+  "total_flos": 5322104911872000.0,
   "trial_name": null,
   "trial_params": null
 }