Training in progress, epoch 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840a92318f61fb69dfa182efe684dee99a3da41ff831a2d13605a5bfda5b237a
+oid sha256:93ed9d910865c040bb4e8228d8f17e050d4abd7fa4567fae0f618649423c3459
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18fb9f5b0c6be125bf8e33bedf2743d20c16b806eea2d63e93bbcc2df2c1e5e4
+oid sha256:48f62a3434f2b8e8744dc25ea578e1b6786d5d9dab5d6a0b654cb08f8e0804d1
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31ead472a288ebb053d701bd95414927cdbca7ca1cfd07450fda73d4911fe2c0
+oid sha256:0009e9c2bcc220e59267f52f8156b8d01b9e750bb5f6a74945612a1026990d89
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e15441b49e878da620ad3310232c539e63deb05abff50db000f873f37bfdb8d
+oid sha256:12f661b61f73b13b74450e15d45c319ce94ca9d3f4730beaaa9e2ebd1092cf2c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 13743,
+  "global_step": 15270,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -966,6 +966,111 @@
       "learning_rate": 0.00011211717709720373,
       "loss": 0.1898,
       "step": 13700
+    },
+    {
+      "epoch": 9.037328094302554,
+      "grad_norm": 0.8357772827148438,
+      "learning_rate": 0.00011145139813581891,
+      "loss": 0.1514,
+      "step": 13800
+    },
+    {
+      "epoch": 9.102815979043877,
+      "grad_norm": 0.7970616817474365,
+      "learning_rate": 0.00011078561917443409,
+      "loss": 0.1537,
+      "step": 13900
+    },
+    {
+      "epoch": 9.1683038637852,
+      "grad_norm": 1.1566450595855713,
+      "learning_rate": 0.00011011984021304926,
+      "loss": 0.1538,
+      "step": 14000
+    },
+    {
+      "epoch": 9.233791748526523,
+      "grad_norm": 0.8751351237297058,
+      "learning_rate": 0.00010945406125166447,
+      "loss": 0.1494,
+      "step": 14100
+    },
+    {
+      "epoch": 9.299279633267846,
+      "grad_norm": 0.8269241452217102,
+      "learning_rate": 0.00010878828229027964,
+      "loss": 0.1555,
+      "step": 14200
+    },
+    {
+      "epoch": 9.364767518009169,
+      "grad_norm": 1.342864990234375,
+      "learning_rate": 0.00010812250332889482,
+      "loss": 0.1622,
+      "step": 14300
+    },
+    {
+      "epoch": 9.430255402750491,
+      "grad_norm": 1.0193088054656982,
+      "learning_rate": 0.00010745672436751,
+      "loss": 0.1574,
+      "step": 14400
+    },
+    {
+      "epoch": 9.495743287491814,
+      "grad_norm": 0.3667553663253784,
+      "learning_rate": 0.00010679094540612517,
+      "loss": 0.153,
+      "step": 14500
+    },
+    {
+      "epoch": 9.561231172233137,
+      "grad_norm": 0.8412798047065735,
+      "learning_rate": 0.00010612516644474036,
+      "loss": 0.1646,
+      "step": 14600
+    },
+    {
+      "epoch": 9.62671905697446,
+      "grad_norm": 0.8854599595069885,
+      "learning_rate": 0.00010545938748335554,
+      "loss": 0.1578,
+      "step": 14700
+    },
+    {
+      "epoch": 9.692206941715783,
+      "grad_norm": 0.6291230916976929,
+      "learning_rate": 0.00010479360852197071,
+      "loss": 0.1571,
+      "step": 14800
+    },
+    {
+      "epoch": 9.757694826457106,
+      "grad_norm": 1.2499074935913086,
+      "learning_rate": 0.00010412782956058589,
+      "loss": 0.1698,
+      "step": 14900
+    },
+    {
+      "epoch": 9.82318271119843,
+      "grad_norm": 0.8760678768157959,
+      "learning_rate": 0.00010346205059920106,
+      "loss": 0.1564,
+      "step": 15000
+    },
+    {
+      "epoch": 9.88867059593975,
+      "grad_norm": 0.6060988306999207,
+      "learning_rate": 0.00010279627163781624,
+      "loss": 0.1692,
+      "step": 15100
+    },
+    {
+      "epoch": 9.954158480681073,
+      "grad_norm": 0.3887087106704712,
+      "learning_rate": 0.00010213049267643142,
+      "loss": 0.1606,
+      "step": 15200
     }
   ],
   "logging_steps": 100,
@@ -985,7 +1090,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.174188457538355e+16,
+  "total_flos": 5.749098290977178e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null