Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f6fea5ad404951ef6a1fae3508ebdd797dc7d0856e4e095dbade4d136af05bb
+oid sha256:9b4e9fe3a11c0765df2ef2a681de6cf73de293693def2c6626a8db4db4156545
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e75175f411e54f2d45a172225b45542e61e14c9898d23196763485fc6e8cdc2
+oid sha256:5270fd8e4813d1c8e4a7815db833fb6624cf3f6f7acb5c7123e1c05b3ca089ff
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8897608d343d62eeb1707c720b184d47499c9ca79a71524526ea1ab75dc3c5d
+oid sha256:dbc86b826bc6bd97d977ae368482d2b94ac269f5ff72bde8fe20b71551da06c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3669724770642202,
+  "epoch": 1.2844036697247707,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,102 @@
       "eval_samples_per_second": 763.509,
       "eval_steps_per_second": 99.588,
       "step": 10
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 0.4800911843776703,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 6.9237,
+      "step": 12
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.5088721513748169,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 6.9119,
+      "step": 15
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "eval_loss": 6.901125907897949,
+      "eval_runtime": 0.0697,
+      "eval_samples_per_second": 660.168,
+      "eval_steps_per_second": 86.109,
+      "step": 15
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 0.5459818840026855,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 6.8969,
+      "step": 18
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "eval_loss": 6.87958288192749,
+      "eval_runtime": 0.058,
+      "eval_samples_per_second": 793.383,
+      "eval_steps_per_second": 103.485,
+      "step": 20
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 0.5402729511260986,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 6.8852,
+      "step": 21
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 0.5008237361907959,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 6.8723,
+      "step": 24
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "eval_loss": 6.86152982711792,
+      "eval_runtime": 0.0589,
+      "eval_samples_per_second": 781.084,
+      "eval_steps_per_second": 101.881,
+      "step": 25
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 0.4618155360221863,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 6.8632,
+      "step": 27
+    },
+    {
+      "epoch": 1.1009174311926606,
+      "grad_norm": 0.4284931719303131,
+      "learning_rate": 5e-05,
+      "loss": 8.6369,
+      "step": 30
+    },
+    {
+      "epoch": 1.1009174311926606,
+      "eval_loss": 6.850541591644287,
+      "eval_runtime": 0.0613,
+      "eval_samples_per_second": 750.191,
+      "eval_steps_per_second": 97.851,
+      "step": 30
+    },
+    {
+      "epoch": 1.2110091743119267,
+      "grad_norm": 0.37953659892082214,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 6.7564,
+      "step": 33
+    },
+    {
+      "epoch": 1.2844036697247707,
+      "eval_loss": 6.844419956207275,
+      "eval_runtime": 0.0605,
+      "eval_samples_per_second": 759.745,
+      "eval_steps_per_second": 99.097,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -71,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 225865089024.0,
+  "total_flos": 774308775936.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null