Training in progress, step 252, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc6d404f7fd69fe907c7d54d9d2ba1b802a5e0867a87634f546ea28477a5f17
+oid sha256:4c4d1afd543174e3ab9a2fe34af04ea8af62f4a7862fc78925dd62a536e9feaf
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ee2b6ae3076a559fcb80a8ff9862fd211c95d781fac1e407e8f1030ac38660
+oid sha256:c67f2182ec15d55237558a16b27d2d849447fdca6258247107fbf31c03b1c68d
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a58fcd0d4e63bda996273295cf19629f45f15b4f31eb5cecaee6502ebb86992
+oid sha256:fa5a85cd5fb1a43d1a3608369f309632ab765e2fc493019f6bf624d685f85850
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd95a1db0e917ddf11b12a343f06e907fcec4b81104002e2471b4778587b465
+oid sha256:ee19ddad9c4c375a1de2d74fb4c1cf5e15d36c1ed47a2cb80f7cb0fbacb3b29e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04402054292002935,
+  "epoch": 0.05282465150403522,
   "eval_steps": 42,
-  "global_step": 210,
+  "global_step": 252,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -545,6 +545,112 @@
       "eval_samples_per_second": 48.679,
       "eval_steps_per_second": 6.089,
       "step": 210
+    },
+    {
+      "epoch": 0.04464940781888691,
+      "grad_norm": 0.3846144676208496,
+      "learning_rate": 6.330184227833376e-05,
+      "loss": 1.0922,
+      "step": 213
+    },
+    {
+      "epoch": 0.04527827271774447,
+      "grad_norm": 0.37346020340919495,
+      "learning_rate": 6.237238428024572e-05,
+      "loss": 1.0727,
+      "step": 216
+    },
+    {
+      "epoch": 0.045907137616602034,
+      "grad_norm": 0.3563274145126343,
+      "learning_rate": 6.143834918526527e-05,
+      "loss": 1.144,
+      "step": 219
+    },
+    {
+      "epoch": 0.0465360025154596,
+      "grad_norm": 0.3684130907058716,
+      "learning_rate": 6.0500082534642464e-05,
+      "loss": 1.0526,
+      "step": 222
+    },
+    {
+      "epoch": 0.047164867414317156,
+      "grad_norm": 0.37623313069343567,
+      "learning_rate": 5.955793143506863e-05,
+      "loss": 1.0694,
+      "step": 225
+    },
+    {
+      "epoch": 0.04779373231317472,
+      "grad_norm": 0.335705429315567,
+      "learning_rate": 5.861224443026595e-05,
+      "loss": 1.0766,
+      "step": 228
+    },
+    {
+      "epoch": 0.04842259721203228,
+      "grad_norm": 0.35654446482658386,
+      "learning_rate": 5.766337137204579e-05,
+      "loss": 1.091,
+      "step": 231
+    },
+    {
+      "epoch": 0.04905146211088984,
+      "grad_norm": 0.33855140209198,
+      "learning_rate": 5.6711663290882776e-05,
+      "loss": 1.0715,
+      "step": 234
+    },
+    {
+      "epoch": 0.04968032700974741,
+      "grad_norm": 0.3658079206943512,
+      "learning_rate": 5.575747226605298e-05,
+      "loss": 1.0915,
+      "step": 237
+    },
+    {
+      "epoch": 0.050309191908604965,
+      "grad_norm": 0.3918761610984802,
+      "learning_rate": 5.480115129538409e-05,
+      "loss": 1.073,
+      "step": 240
+    },
+    {
+      "epoch": 0.05093805680746253,
+      "grad_norm": 0.37080520391464233,
+      "learning_rate": 5.384305416466584e-05,
+      "loss": 1.0234,
+      "step": 243
+    },
+    {
+      "epoch": 0.051566921706320094,
+      "grad_norm": 0.315390020608902,
+      "learning_rate": 5.288353531676873e-05,
+      "loss": 1.0456,
+      "step": 246
+    },
+    {
+      "epoch": 0.05219578660517765,
+      "grad_norm": 0.34985366463661194,
+      "learning_rate": 5.192294972051992e-05,
+      "loss": 1.0505,
+      "step": 249
+    },
+    {
+      "epoch": 0.05282465150403522,
+      "grad_norm": 0.35391372442245483,
+      "learning_rate": 5.0961652739384356e-05,
+      "loss": 1.0728,
+      "step": 252
+    },
+    {
+      "epoch": 0.05282465150403522,
+      "eval_loss": 1.0837104320526123,
+      "eval_runtime": 164.9887,
+      "eval_samples_per_second": 48.7,
+      "eval_steps_per_second": 6.091,
+      "step": 252
     }
   ],
   "logging_steps": 3,
@@ -564,7 +670,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.479610490191872e+16,
+  "total_flos": 5.375532588230246e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null