Training in progress, epoch 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31ff5b73762c4ae792ae7f3f219e10061f29a8f3b60e2fadee6b97cc45c1cdb
+oid sha256:840a92318f61fb69dfa182efe684dee99a3da41ff831a2d13605a5bfda5b237a
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b90890932f7fe71b0defece74b2b2f00c1fe185289d551d061a7932efbff82b
+oid sha256:18fb9f5b0c6be125bf8e33bedf2743d20c16b806eea2d63e93bbcc2df2c1e5e4
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd22df0cd08ad15cc846a5018cba8d1f8ff40c8aa961fa9e9a7835026c44b248
+oid sha256:31ead472a288ebb053d701bd95414927cdbca7ca1cfd07450fda73d4911fe2c0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ccacca645aae41a4293a2aa37acee9e2b809b960d8056116131a8730010aef
+oid sha256:8e15441b49e878da620ad3310232c539e63deb05abff50db000f873f37bfdb8d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.0,
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 12216,
+  "global_step": 13743,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -861,6 +861,111 @@
       "learning_rate": 0.00012210386151797602,
       "loss": 0.1897,
       "step": 12200
+    },
+    {
+      "epoch": 8.055009823182711,
+      "grad_norm": 1.205670714378357,
+      "learning_rate": 0.00012143808255659121,
+      "loss": 0.1626,
+      "step": 12300
+    },
+    {
+      "epoch": 8.120497707924034,
+      "grad_norm": 0.502905547618866,
+      "learning_rate": 0.00012077230359520639,
+      "loss": 0.1598,
+      "step": 12400
+    },
+    {
+      "epoch": 8.185985592665357,
+      "grad_norm": 1.0201475620269775,
+      "learning_rate": 0.00012010652463382157,
+      "loss": 0.1721,
+      "step": 12500
+    },
+    {
+      "epoch": 8.25147347740668,
+      "grad_norm": 0.6289061903953552,
+      "learning_rate": 0.00011944074567243674,
+      "loss": 0.1646,
+      "step": 12600
+    },
+    {
+      "epoch": 8.316961362148003,
+      "grad_norm": 1.2342171669006348,
+      "learning_rate": 0.00011877496671105193,
+      "loss": 0.1675,
+      "step": 12700
+    },
+    {
+      "epoch": 8.382449246889326,
+      "grad_norm": 0.6001673340797424,
+      "learning_rate": 0.00011810918774966711,
+      "loss": 0.1673,
+      "step": 12800
+    },
+    {
+      "epoch": 8.447937131630649,
+      "grad_norm": 0.9419691562652588,
+      "learning_rate": 0.00011744340878828231,
+      "loss": 0.1621,
+      "step": 12900
+    },
+    {
+      "epoch": 8.513425016371972,
+      "grad_norm": 0.6249241828918457,
+      "learning_rate": 0.00011677762982689749,
+      "loss": 0.1673,
+      "step": 13000
+    },
+    {
+      "epoch": 8.578912901113295,
+      "grad_norm": 1.8031052350997925,
+      "learning_rate": 0.00011611185086551266,
+      "loss": 0.1742,
+      "step": 13100
+    },
+    {
+      "epoch": 8.644400785854616,
+      "grad_norm": 0.8871346712112427,
+      "learning_rate": 0.00011544607190412784,
+      "loss": 0.1725,
+      "step": 13200
+    },
+    {
+      "epoch": 8.709888670595939,
+      "grad_norm": 1.4257563352584839,
+      "learning_rate": 0.00011478029294274302,
+      "loss": 0.1617,
+      "step": 13300
+    },
+    {
+      "epoch": 8.775376555337262,
+      "grad_norm": 10.05364990234375,
+      "learning_rate": 0.00011411451398135819,
+      "loss": 0.1743,
+      "step": 13400
+    },
+    {
+      "epoch": 8.840864440078585,
+      "grad_norm": 0.492718905210495,
+      "learning_rate": 0.00011344873501997337,
+      "loss": 0.1718,
+      "step": 13500
+    },
+    {
+      "epoch": 8.906352324819908,
+      "grad_norm": 3.150280237197876,
+      "learning_rate": 0.00011278295605858856,
+      "loss": 0.1719,
+      "step": 13600
+    },
+    {
+      "epoch": 8.97184020956123,
+      "grad_norm": 3.0732333660125732,
+      "learning_rate": 0.00011211717709720373,
+      "loss": 0.1898,
+      "step": 13700
     }
   ],
   "logging_steps": 100,
@@ -880,7 +985,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.599278634165862e+16,
+  "total_flos": 5.174188457538355e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null