Upload model v0.1-wip-4200

config.json

@@ -31,9 +31,5 @@
   "tie_word_embeddings": true,
   "transformers_version": "5.8.0",
   "use_cache": false,
-  "vocab_size": 133,
-  "auto_map": {
-    "AutoModelForCausalLM": "conditioned_gpt2.ConditionedGPT2"
-  },
-  "num_pokemon": 2227
-}
+  "vocab_size": 133
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0660160dc76c8c20854489602c8da7876eb9ef4f76343e0f129223530fb2a161
+oid sha256:515ceb8d5ff4341e36d7d7c5fe8fde8d6940ab46dbf6a1bd79dd36012f7321e9
 size 164952636

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aee0e000a44c65ee74b0860659bac260efa097500e7c6d0793441e28c3ff334c
+oid sha256:52fad57978910131b86131a6a0ae6a26496741a63a801158b9d0596f923bb86e
 size 330005818

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d861a0f5d12616551057402bc2ac851ec83eb34a7f0cdd6af00b05e9744ffc23
+oid sha256:cb12d6e5082ab1d7a41d1b0e160bcd6a9dc3763088747fc64e4a4e9506b732a7
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0959c12ed031011a1fc7f89c1b203470f1a77ddea2d937e94fe43b753340beaa
+oid sha256:52218e8ad6f0dafdcf777603e7f1c355870364f1e2aeaf950202d6398a61feab
 size 1064

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.264485344239946,
+  "epoch": 11.444444444444445,
   "eval_steps": 500,
-  "global_step": 3400,
+  "global_step": 4200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -484,6 +484,118 @@
       "learning_rate": 0.000209766773095578,
       "loss": 1.3368931579589844,
       "step": 3400
+    },
+    {
+      "epoch": 9.400817995910021,
+      "grad_norm": 1.3249437808990479,
+      "learning_rate": 0.00020121405670051008,
+      "loss": 1.297091064453125,
+      "step": 3450
+    },
+    {
+      "epoch": 9.537150647580095,
+      "grad_norm": 1.3749561309814453,
+      "learning_rate": 0.00019275047873167374,
+      "loss": 1.260106658935547,
+      "step": 3500
+    },
+    {
+      "epoch": 9.67348329925017,
+      "grad_norm": 1.4010766744613647,
+      "learning_rate": 0.0001843836762070014,
+      "loss": 1.239128646850586,
+      "step": 3550
+    },
+    {
+      "epoch": 9.809815950920246,
+      "grad_norm": 1.5308102369308472,
+      "learning_rate": 0.00017612119882015126,
+      "loss": 1.1977056121826173,
+      "step": 3600
+    },
+    {
+      "epoch": 9.94614860259032,
+      "grad_norm": 1.3873751163482666,
+      "learning_rate": 0.00016797050212812275,
+      "loss": 1.1842040252685546,
+      "step": 3650
+    },
+    {
+      "epoch": 10.081799591002046,
+      "grad_norm": 1.3666012287139893,
+      "learning_rate": 0.00015993894082381616,
+      "loss": 1.1095658111572266,
+      "step": 3700
+    },
+    {
+      "epoch": 10.21813224267212,
+      "grad_norm": 1.3528972864151,
+      "learning_rate": 0.00015203376209960474,
+      "loss": 1.103120346069336,
+      "step": 3750
+    },
+    {
+      "epoch": 10.354464894342195,
+      "grad_norm": 1.3081281185150146,
+      "learning_rate": 0.00014426209910790887,
+      "loss": 1.0691104125976563,
+      "step": 3800
+    },
+    {
+      "epoch": 10.49079754601227,
+      "grad_norm": 1.3515572547912598,
+      "learning_rate": 0.00013663096452467343,
+      "loss": 1.0644143676757813,
+      "step": 3850
+    },
+    {
+      "epoch": 10.627130197682344,
+      "grad_norm": 1.2935131788253784,
+      "learning_rate": 0.00012914724422155598,
+      "loss": 1.0334495544433593,
+      "step": 3900
+    },
+    {
+      "epoch": 10.76346284935242,
+      "grad_norm": 1.3209459781646729,
+      "learning_rate": 0.00012181769105253435,
+      "loss": 1.0103805541992188,
+      "step": 3950
+    },
+    {
+      "epoch": 10.899795501022496,
+      "grad_norm": 1.324385643005371,
+      "learning_rate": 0.00011464891876054252,
+      "loss": 0.990460433959961,
+      "step": 4000
+    },
+    {
+      "epoch": 11.03544648943422,
+      "grad_norm": 1.374879002571106,
+      "learning_rate": 0.00010764739600963116,
+      "loss": 0.9643755340576172,
+      "step": 4050
+    },
+    {
+      "epoch": 11.171779141104295,
+      "grad_norm": 1.275993824005127,
+      "learning_rate": 0.00010081944054803842,
+      "loss": 0.936119155883789,
+      "step": 4100
+    },
+    {
+      "epoch": 11.308111792774369,
+      "grad_norm": 1.2590258121490479,
+      "learning_rate": 9.417121350743844e-05,
+      "loss": 0.9281440734863281,
+      "step": 4150
+    },
+    {
+      "epoch": 11.444444444444445,
+      "grad_norm": 1.2088381052017212,
+      "learning_rate": 8.770871384351085e-05,
+      "loss": 0.9070972442626953,
+      "step": 4200
     }
   ],
   "logging_steps": 50,
@@ -503,7 +615,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.086762739654984e+17,
+  "total_flos": 9.989600444122399e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null