Training in progress, step 43, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b633bd9b84855b36e6ac4b2cf64d7e193c76ddc9c974ab43922f0e76943413d
+oid sha256:822bc2ffc730d54c877acb1f40f8698afc4976d1824333455c8d315f85280e4e
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfdf4149a5e87f8b83197736fb664979cebab862c1edb9a18e3260d3a8d92d24
+oid sha256:612b269f60aca2c96227b2d18b3be85eb8b027ab3ec20db0f6fb0e8a4f8c1295
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9b00701ad406b233e90580e75f7ed0383a04455271c95bb801f9d94622a692
+oid sha256:2da2ff6f33c98d8795d59988d31e2854b66c40ed5f9eb5ae518eb81c6c4dab51
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25df3916ccfae1c1b3e9499a3f64a8b40993e0159cd20256e1c78e9e43cf002
+oid sha256:62301e80c7598b8950632611ebfa03646637d97848f872bf7d1a304382a034d4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:486f5c9146b839d67ba97683afc65b7e7e6411bd9fe1e990efb82c4fa5d3f379
+oid sha256:f0a0b7eac5d5eeb6a82e665caa24d67eaf6d4ac0cd22b33a51fa0a9847ed1fb3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e5bfe11cacea66e6fe0b79d2f840c9f45565f7f5be639a5adbe2d9186857c86
+oid sha256:416c1afc422120318bfb15e151d140e32cb7366313329428b2e93cdac85c2615
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f73e6deadf3f08547d8bef9e9b3d87995c0c2ef87d51b8801270b8b2d32ac55
+oid sha256:d9ca16dc5125aa616f8880e7477dabd4029e096d950b1e4b31474d314c00eace
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7817371937639197,
+  "epoch": 3.0645879732739423,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 43,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,132 @@
       "eval_samples_per_second": 33.509,
       "eval_steps_per_second": 8.712,
       "step": 25
+    },
+    {
+      "epoch": 1.8530066815144766,
+      "grad_norm": 0.8329769372940063,
+      "learning_rate": 4.307583240115024e-05,
+      "loss": 0.1588,
+      "step": 26
+    },
+    {
+      "epoch": 1.9242761692650334,
+      "grad_norm": 1.176580548286438,
+      "learning_rate": 3.9789240471617385e-05,
+      "loss": 0.1374,
+      "step": 27
+    },
+    {
+      "epoch": 1.9955456570155903,
+      "grad_norm": 0.6185368895530701,
+      "learning_rate": 3.659191132728971e-05,
+      "loss": 0.2032,
+      "step": 28
+    },
+    {
+      "epoch": 2.066815144766147,
+      "grad_norm": 3.2315216064453125,
+      "learning_rate": 3.350260816694816e-05,
+      "loss": 0.514,
+      "step": 29
+    },
+    {
+      "epoch": 2.138084632516704,
+      "grad_norm": 0.7700513601303101,
+      "learning_rate": 3.0539460249945056e-05,
+      "loss": 0.1931,
+      "step": 30
+    },
+    {
+      "epoch": 2.2093541202672604,
+      "grad_norm": 0.5963460206985474,
+      "learning_rate": 2.7719856506501306e-05,
+      "loss": 0.1288,
+      "step": 31
+    },
+    {
+      "epoch": 2.2806236080178173,
+      "grad_norm": 0.5300996899604797,
+      "learning_rate": 2.5060343492549566e-05,
+      "loss": 0.1928,
+      "step": 32
+    },
+    {
+      "epoch": 2.351893095768374,
+      "grad_norm": 0.9159259796142578,
+      "learning_rate": 2.257652828796459e-05,
+      "loss": 0.1928,
+      "step": 33
+    },
+    {
+      "epoch": 2.423162583518931,
+      "grad_norm": 0.8254880905151367,
+      "learning_rate": 2.0282986908012567e-05,
+      "loss": 0.1319,
+      "step": 34
+    },
+    {
+      "epoch": 2.494432071269488,
+      "grad_norm": 0.6946773529052734,
+      "learning_rate": 1.819317876549771e-05,
+      "loss": 0.2188,
+      "step": 35
+    },
+    {
+      "epoch": 2.5657015590200447,
+      "grad_norm": 0.7235588431358337,
+      "learning_rate": 1.631936768557596e-05,
+      "loss": 0.2069,
+      "step": 36
+    },
+    {
+      "epoch": 2.6369710467706016,
+      "grad_norm": 0.5640904903411865,
+      "learning_rate": 1.4672549936752506e-05,
+      "loss": 0.1033,
+      "step": 37
+    },
+    {
+      "epoch": 2.708240534521158,
+      "grad_norm": 0.5563797354698181,
+      "learning_rate": 1.3262389700405744e-05,
+      "loss": 0.1157,
+      "step": 38
+    },
+    {
+      "epoch": 2.779510022271715,
+      "grad_norm": 0.6494319438934326,
+      "learning_rate": 1.2097162357528127e-05,
+      "loss": 0.2194,
+      "step": 39
+    },
+    {
+      "epoch": 2.8507795100222717,
+      "grad_norm": 0.6779353022575378,
+      "learning_rate": 1.1183705925499948e-05,
+      "loss": 0.1103,
+      "step": 40
+    },
+    {
+      "epoch": 2.9220489977728286,
+      "grad_norm": 0.7211727499961853,
+      "learning_rate": 1.0527380929884324e-05,
+      "loss": 0.1513,
+      "step": 41
+    },
+    {
+      "epoch": 2.9933184855233854,
+      "grad_norm": 0.5112365484237671,
+      "learning_rate": 1.013203894673168e-05,
+      "loss": 0.1698,
+      "step": 42
+    },
+    {
+      "epoch": 3.0645879732739423,
+      "grad_norm": 5.871841907501221,
+      "learning_rate": 1e-05,
+      "loss": 0.5043,
+      "step": 43
     }
   ],
   "logging_steps": 1,
@@ -212,12 +338,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.347180870336512e+16,
+  "total_flos": 4.049313816222106e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null