Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d561a3f3cc8d1c19a681c061d5d87b02227f393e135edfdd554f053c11ef586
+oid sha256:5db89031f861b351398579fdeed7f2fb75adc951da6bbb79461eec30cb42cae7
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b3a2113ecb1b446af5ca68d8fd507dc873f1535a9c75c3e8a47d5246923db5
+oid sha256:c83434275e79d234627e39a2ec4efe033481954aab821806a1dfd2935bd20358
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50eebf8d061e3255b63fc3a2dc3ef02231d3653b40f92cb4b4beca7dd60219ae
+oid sha256:b699cd69e707818116cdde38e402657f6f0fe8cde3928db61304dd17c81e968e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34f9c194f14d5c67265ac71b8d34cb6f960441ca9a99e80d33d78e02859e649b
+oid sha256:afb9c3c0c925ea8cf32a1dcba2e2f6242aaac5236534a8df451537dd590ac10a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.034601788313578706,
+  "epoch": 0.05190268247036806,
   "eval_steps": 50,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -197,6 +197,97 @@
       "learning_rate": 0.0001492129799588288,
       "loss": 49.3161,
       "step": 26
+    },
+    {
+      "epoch": 0.03593262632563943,
+      "grad_norm": 4.290125846862793,
+      "learning_rate": 0.0001489294560698738,
+      "loss": 48.7192,
+      "step": 27
+    },
+    {
+      "epoch": 0.03726346433770015,
+      "grad_norm": 4.7845635414123535,
+      "learning_rate": 0.000148602759460456,
+      "loss": 47.9046,
+      "step": 28
+    },
+    {
+      "epoch": 0.03859430234976086,
+      "grad_norm": 9.48447036743164,
+      "learning_rate": 0.0001482330809121954,
+      "loss": 47.9862,
+      "step": 29
+    },
+    {
+      "epoch": 0.039925140361821584,
+      "grad_norm": 5.269348621368408,
+      "learning_rate": 0.00014782063630695388,
+      "loss": 47.6904,
+      "step": 30
+    },
+    {
+      "epoch": 0.041255978373882306,
+      "grad_norm": 4.928490161895752,
+      "learning_rate": 0.00014736566650076636,
+      "loss": 48.8313,
+      "step": 31
+    },
+    {
+      "epoch": 0.04258681638594302,
+      "grad_norm": 5.5268449783325195,
+      "learning_rate": 0.00014686843718318744,
+      "loss": 47.7213,
+      "step": 32
+    },
+    {
+      "epoch": 0.04391765439800374,
+      "grad_norm": 4.2176079750061035,
+      "learning_rate": 0.00014632923872213652,
+      "loss": 47.0136,
+      "step": 33
+    },
+    {
+      "epoch": 0.04524849241006446,
+      "grad_norm": 4.410348892211914,
+      "learning_rate": 0.0001457483859943307,
+      "loss": 45.6157,
+      "step": 34
+    },
+    {
+      "epoch": 0.046579330422125184,
+      "grad_norm": 4.219701766967773,
+      "learning_rate": 0.00014512621820140611,
+      "loss": 47.701,
+      "step": 35
+    },
+    {
+      "epoch": 0.0479101684341859,
+      "grad_norm": 4.424015522003174,
+      "learning_rate": 0.0001444630986718332,
+      "loss": 45.6344,
+      "step": 36
+    },
+    {
+      "epoch": 0.04924100644624662,
+      "grad_norm": 4.436514854431152,
+      "learning_rate": 0.00014375941464874368,
+      "loss": 46.8412,
+      "step": 37
+    },
+    {
+      "epoch": 0.05057184445830734,
+      "grad_norm": 4.463353157043457,
+      "learning_rate": 0.0001430155770637909,
+      "loss": 45.4691,
+      "step": 38
+    },
+    {
+      "epoch": 0.05190268247036806,
+      "grad_norm": 5.982223033905029,
+      "learning_rate": 0.00014223202029717776,
+      "loss": 46.5923,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -216,7 +307,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.484068172762972e+17,
+  "total_flos": 2.207202166135849e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null