Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e201cb9cff52f30bf5ae9ea51508e46e10420b2a220ea7f3245f8e692808e0c
+oid sha256:5b1e5ae09b2358a7cec14ebf082c6791eb4b2371a0e0e0f881d1f2f7de4e2d1e
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5b76d64e67de9fd356021a9eb396e88a7e41adc982a1e266fc6fced3b5b2a9
+oid sha256:4e72e98a3f824f25f6d07ecdaffef31b797d3c943bad0324510fdfec7d11d317
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2878759bee0a12cd28952503c327798cb375b6062d6ba2ce8f13fa04c9ecf2c1
+oid sha256:bc78e937af6df61002f0454d4a89f4506e44ed33ab12b2726e58d84741b9206e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0023502867349816676,
+  "epoch": 0.004700573469963335,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 29.216,
       "eval_steps_per_second": 14.608,
       "step": 25
+    },
+    {
+      "epoch": 0.0024442982043809346,
+      "grad_norm": 1.5596882104873657,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.996,
+      "step": 26
+    },
+    {
+      "epoch": 0.002538309673780201,
+      "grad_norm": 1.2554572820663452,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.7677,
+      "step": 27
+    },
+    {
+      "epoch": 0.002632321143179468,
+      "grad_norm": 1.1897380352020264,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.8327,
+      "step": 28
+    },
+    {
+      "epoch": 0.0027263326125787344,
+      "grad_norm": 1.1996997594833374,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.7552,
+      "step": 29
+    },
+    {
+      "epoch": 0.0028203440819780014,
+      "grad_norm": 1.190172553062439,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.6472,
+      "step": 30
+    },
+    {
+      "epoch": 0.002914355551377268,
+      "grad_norm": 1.0043503046035767,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.5782,
+      "step": 31
+    },
+    {
+      "epoch": 0.0030083670207765346,
+      "grad_norm": 0.9340465068817139,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.5787,
+      "step": 32
+    },
+    {
+      "epoch": 0.0031023784901758012,
+      "grad_norm": 1.2603780031204224,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.6059,
+      "step": 33
+    },
+    {
+      "epoch": 0.0031963899595750683,
+      "grad_norm": 1.4247483015060425,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.6423,
+      "step": 34
+    },
+    {
+      "epoch": 0.003290401428974335,
+      "grad_norm": 0.9418686032295227,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.522,
+      "step": 35
+    },
+    {
+      "epoch": 0.0033844128983736015,
+      "grad_norm": 1.142016887664795,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.6962,
+      "step": 36
+    },
+    {
+      "epoch": 0.003478424367772868,
+      "grad_norm": 1.1568361520767212,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.5529,
+      "step": 37
+    },
+    {
+      "epoch": 0.003572435837172135,
+      "grad_norm": 1.2142870426177979,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.4753,
+      "step": 38
+    },
+    {
+      "epoch": 0.0036664473065714017,
+      "grad_norm": 1.2301100492477417,
+      "learning_rate": 5e-05,
+      "loss": 0.5065,
+      "step": 39
+    },
+    {
+      "epoch": 0.0037604587759706683,
+      "grad_norm": 1.3371412754058838,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.4529,
+      "step": 40
+    },
+    {
+      "epoch": 0.0038544702453699353,
+      "grad_norm": 0.9668884873390198,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.4737,
+      "step": 41
+    },
+    {
+      "epoch": 0.0039484817147692015,
+      "grad_norm": 1.0440391302108765,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5063,
+      "step": 42
+    },
+    {
+      "epoch": 0.004042493184168469,
+      "grad_norm": 1.243342638015747,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.3832,
+      "step": 43
+    },
+    {
+      "epoch": 0.004136504653567736,
+      "grad_norm": 1.4090092182159424,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.6327,
+      "step": 44
+    },
+    {
+      "epoch": 0.004230516122967002,
+      "grad_norm": 1.3914059400558472,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4771,
+      "step": 45
+    },
+    {
+      "epoch": 0.004324527592366269,
+      "grad_norm": 1.1954938173294067,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.4217,
+      "step": 46
+    },
+    {
+      "epoch": 0.004418539061765535,
+      "grad_norm": 1.7103815078735352,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.4914,
+      "step": 47
+    },
+    {
+      "epoch": 0.004512550531164802,
+      "grad_norm": 1.5357106924057007,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.456,
+      "step": 48
+    },
+    {
+      "epoch": 0.004606562000564069,
+      "grad_norm": 1.7698625326156616,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.4604,
+      "step": 49
+    },
+    {
+      "epoch": 0.004700573469963335,
+      "grad_norm": 2.5681278705596924,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.4387,
+      "step": 50
+    },
+    {
+      "epoch": 0.004700573469963335,
+      "eval_loss": 0.6145913004875183,
+      "eval_runtime": 306.57,
+      "eval_samples_per_second": 29.22,
+      "eval_steps_per_second": 14.61,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5208852450508800.0,
+  "total_flos": 1.04177049010176e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null