Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0688474f1bf024620068b5c32f665b6fb09610e73959079013271ebe44da9f9c
+oid sha256:bd1a841fe06df2853fbd416cdc8d079cc531d947e13cc486f09f2bf14ee91d69
 size 407179392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1236f2d6b3e24f640e4fa432d67d1a4626a32b15a696fa095be6faaafc57c47b
+oid sha256:22480292f7d6813921a3064dc9a64c13b8e3536ecbe8984008c1fe7db58637a9
 size 109342998

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe21e0569e934ade38e8e5ab1c44c3bb29781c9068a7637f850c09cf55d86fc5
+oid sha256:c242a91be9cfcabf4b35bd27e771f2777f257c530adf560f58a0f34ab68510e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:530e1876edecc7a14181b17d14f75fb7d2b1b392457fd4e51b5ee70d940c8a90
+oid sha256:b04614c3fedfb0bab0db621905a752b151866b1995a65909c46af0471d274d85
 size 2080

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00012135097614725212,
+  "epoch": 0.00014562117137670256,
   "eval_steps": 10,
-  "global_step": 50,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,84 @@
       "eval_samples_per_second": 0.448,
       "eval_steps_per_second": 0.448,
       "step": 50
+    },
+    {
+      "epoch": 0.00012377799567019716,
+      "grad_norm": 3.4755067825317383,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 1.2644,
+      "step": 51
+    },
+    {
+      "epoch": 0.0001262050151931422,
+      "grad_norm": 3.064790725708008,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 0.816,
+      "step": 52
+    },
+    {
+      "epoch": 0.00012863203471608726,
+      "grad_norm": 6.472192764282227,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 3.0402,
+      "step": 53
+    },
+    {
+      "epoch": 0.00013105905423903229,
+      "grad_norm": 6.017213821411133,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 1.9637,
+      "step": 54
+    },
+    {
+      "epoch": 0.00013348607376197734,
+      "grad_norm": 2.969481945037842,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 1.0158,
+      "step": 55
+    },
+    {
+      "epoch": 0.0001359130932849224,
+      "grad_norm": 4.294132709503174,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 2.329,
+      "step": 56
+    },
+    {
+      "epoch": 0.00013834011280786744,
+      "grad_norm": 2.0407297611236572,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 0.8446,
+      "step": 57
+    },
+    {
+      "epoch": 0.00014076713233081246,
+      "grad_norm": 6.152376174926758,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 1.7769,
+      "step": 58
+    },
+    {
+      "epoch": 0.0001431941518537575,
+      "grad_norm": 5.564684867858887,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 1.8718,
+      "step": 59
+    },
+    {
+      "epoch": 0.00014562117137670256,
+      "grad_norm": 3.1191859245300293,
+      "learning_rate": 0.00019999999494757503,
+      "loss": 1.1267,
+      "step": 60
+    },
+    {
+      "epoch": 0.00014562117137670256,
+      "eval_loss": 2.2274293899536133,
+      "eval_runtime": 46.8696,
+      "eval_samples_per_second": 0.448,
+      "eval_steps_per_second": 0.448,
+      "step": 60
     }
   ],
   "logging_steps": 1,
@@ -424,7 +502,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1091804803891200.0,
+  "total_flos": 1310165764669440.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null