Training in progress, epoch 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4f7252f604cf965972957c688430867f606aac2bec4eb77fb202768aa651f70
+oid sha256:4b4230af128bde58a167471c8faa4ab1796dd0798b459161d7564f9c388265d2
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1090523e29fc489b18443eb3a415b3bb5265e6129512691fad09e588f82982
+oid sha256:88fbfe230bc792a86d0d5bdd5e1799b841e88adae9ba34ce31c97fa350479d89
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a0a70cb7e3a876b8eb26e7da00ee587d5d1961bed884261da996978a8703fd
+oid sha256:07c0416d97a798bdffe510f256377efc10da6f0e64cc0201152b774a9d447d5b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578b41f9923ae9433bb17df44ecd934af6b2b0e1a29240e7817c1990bdf3b072
+oid sha256:87973b5e7af74b70718584fe3c13409a57bdfd5b0680b1f40d5300b1f2913e4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 4581,
+  "global_step": 6108,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -322,6 +322,118 @@
       "learning_rate": 0.0001733688415446072,
       "loss": 0.4335,
       "step": 4500
+    },
+    {
+      "epoch": 3.0124426981008514,
+      "grad_norm": 2.103531837463379,
+      "learning_rate": 0.00017270306258322237,
+      "loss": 0.4031,
+      "step": 4600
+    },
+    {
+      "epoch": 3.0779305828421744,
+      "grad_norm": 1.0188701152801514,
+      "learning_rate": 0.00017203728362183754,
+      "loss": 0.3268,
+      "step": 4700
+    },
+    {
+      "epoch": 3.143418467583497,
+      "grad_norm": 1.5448323488235474,
+      "learning_rate": 0.00017137150466045272,
+      "loss": 0.3513,
+      "step": 4800
+    },
+    {
+      "epoch": 3.20890635232482,
+      "grad_norm": 2.3558382987976074,
+      "learning_rate": 0.00017070572569906792,
+      "loss": 0.3276,
+      "step": 4900
+    },
+    {
+      "epoch": 3.2743942370661427,
+      "grad_norm": 1.2140190601348877,
+      "learning_rate": 0.0001700399467376831,
+      "loss": 0.3424,
+      "step": 5000
+    },
+    {
+      "epoch": 3.3398821218074657,
+      "grad_norm": 1.4044971466064453,
+      "learning_rate": 0.00016937416777629827,
+      "loss": 0.3296,
+      "step": 5100
+    },
+    {
+      "epoch": 3.4053700065487886,
+      "grad_norm": 1.970288872718811,
+      "learning_rate": 0.00016870838881491348,
+      "loss": 0.3302,
+      "step": 5200
+    },
+    {
+      "epoch": 3.4708578912901116,
+      "grad_norm": 3.1513946056365967,
+      "learning_rate": 0.00016804260985352865,
+      "loss": 0.3351,
+      "step": 5300
+    },
+    {
+      "epoch": 3.536345776031434,
+      "grad_norm": 3.6007206439971924,
+      "learning_rate": 0.00016737683089214383,
+      "loss": 0.3379,
+      "step": 5400
+    },
+    {
+      "epoch": 3.601833660772757,
+      "grad_norm": 2.663041353225708,
+      "learning_rate": 0.000166711051930759,
+      "loss": 0.3189,
+      "step": 5500
+    },
+    {
+      "epoch": 3.66732154551408,
+      "grad_norm": 1.3484437465667725,
+      "learning_rate": 0.00016604527296937418,
+      "loss": 0.3369,
+      "step": 5600
+    },
+    {
+      "epoch": 3.732809430255403,
+      "grad_norm": 1.3509025573730469,
+      "learning_rate": 0.00016537949400798936,
+      "loss": 0.3365,
+      "step": 5700
+    },
+    {
+      "epoch": 3.7982973149967254,
+      "grad_norm": 1.4989405870437622,
+      "learning_rate": 0.00016471371504660453,
+      "loss": 0.334,
+      "step": 5800
+    },
+    {
+      "epoch": 3.8637851997380483,
+      "grad_norm": 0.9118553400039673,
+      "learning_rate": 0.0001640479360852197,
+      "loss": 0.3116,
+      "step": 5900
+    },
+    {
+      "epoch": 3.9292730844793713,
+      "grad_norm": 0.6175466775894165,
+      "learning_rate": 0.0001633821571238349,
+      "loss": 0.3217,
+      "step": 6000
+    },
+    {
+      "epoch": 3.9947609692206942,
+      "grad_norm": 1.8679933547973633,
+      "learning_rate": 0.00016271637816245006,
+      "loss": 0.3416,
+      "step": 6100
     }
   ],
   "logging_steps": 100,
@@ -341,7 +453,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7247294894112768e+16,
+  "total_flos": 2.299639319704371e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null