Training in progress, epoch 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4230af128bde58a167471c8faa4ab1796dd0798b459161d7564f9c388265d2
+oid sha256:8666d4b0de1e01f82c2a972c3cc327055e0c45d1a027b222a9b58be16f972b23
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88fbfe230bc792a86d0d5bdd5e1799b841e88adae9ba34ce31c97fa350479d89
+oid sha256:ac16bdc41b1ccb6d62d1c9f1d7d043825aab2a80f7d6b2c10cbc2fe86ee07c60
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c0416d97a798bdffe510f256377efc10da6f0e64cc0201152b774a9d447d5b
+oid sha256:f490d615a5ee7c276bc3c3087f8c609d423adbee91322cc88877232c5f12c8bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87973b5e7af74b70718584fe3c13409a57bdfd5b0680b1f40d5300b1f2913e4c
+oid sha256:eb3f1d8aaf81e8d55005af0a38cd574f62512c26aa1bfacbfb394f3ba5f83f50
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 6108,
+  "global_step": 7635,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -434,6 +434,111 @@
       "learning_rate": 0.00016271637816245006,
       "loss": 0.3416,
       "step": 6100
+    },
+    {
+      "epoch": 4.060248853962017,
+      "grad_norm": 0.7909936308860779,
+      "learning_rate": 0.00016205059920106524,
+      "loss": 0.2607,
+      "step": 6200
+    },
+    {
+      "epoch": 4.12573673870334,
+      "grad_norm": 3.118696451187134,
+      "learning_rate": 0.00016138482023968042,
+      "loss": 0.274,
+      "step": 6300
+    },
+    {
+      "epoch": 4.191224623444663,
+      "grad_norm": 2.2361562252044678,
+      "learning_rate": 0.00016071904127829562,
+      "loss": 0.2613,
+      "step": 6400
+    },
+    {
+      "epoch": 4.256712508185986,
+      "grad_norm": 1.408036708831787,
+      "learning_rate": 0.0001600532623169108,
+      "loss": 0.2707,
+      "step": 6500
+    },
+    {
+      "epoch": 4.322200392927308,
+      "grad_norm": 1.8916605710983276,
+      "learning_rate": 0.00015938748335552597,
+      "loss": 0.2624,
+      "step": 6600
+    },
+    {
+      "epoch": 4.387688277668631,
+      "grad_norm": 2.0656261444091797,
+      "learning_rate": 0.00015872170439414115,
+      "loss": 0.2711,
+      "step": 6700
+    },
+    {
+      "epoch": 4.453176162409954,
+      "grad_norm": 1.0669779777526855,
+      "learning_rate": 0.00015805592543275632,
+      "loss": 0.2764,
+      "step": 6800
+    },
+    {
+      "epoch": 4.518664047151277,
+      "grad_norm": 0.840621292591095,
+      "learning_rate": 0.00015739014647137153,
+      "loss": 0.2853,
+      "step": 6900
+    },
+    {
+      "epoch": 4.5841519318926,
+      "grad_norm": 1.5249924659729004,
+      "learning_rate": 0.0001567243675099867,
+      "loss": 0.2928,
+      "step": 7000
+    },
+    {
+      "epoch": 4.649639816633923,
+      "grad_norm": 1.775383472442627,
+      "learning_rate": 0.00015605858854860188,
+      "loss": 0.2598,
+      "step": 7100
+    },
+    {
+      "epoch": 4.715127701375246,
+      "grad_norm": 1.2116707563400269,
+      "learning_rate": 0.00015539280958721705,
+      "loss": 0.2855,
+      "step": 7200
+    },
+    {
+      "epoch": 4.780615586116569,
+      "grad_norm": 2.191751003265381,
+      "learning_rate": 0.00015472703062583223,
+      "loss": 0.286,
+      "step": 7300
+    },
+    {
+      "epoch": 4.846103470857892,
+      "grad_norm": 2.339139461517334,
+      "learning_rate": 0.0001540612516644474,
+      "loss": 0.2833,
+      "step": 7400
+    },
+    {
+      "epoch": 4.911591355599214,
+      "grad_norm": 0.6427702307701111,
+      "learning_rate": 0.00015339547270306258,
+      "loss": 0.2763,
+      "step": 7500
+    },
+    {
+      "epoch": 4.977079240340537,
+      "grad_norm": 2.4909677505493164,
+      "learning_rate": 0.00015272969374167776,
+      "loss": 0.2755,
+      "step": 7600
     }
   ],
   "logging_steps": 100,
@@ -453,7 +558,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.299639319704371e+16,
+  "total_flos": 2.874549143915725e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null