Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0.dev0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4646da91ff11e1a61634ae865cb49bc18baad0a1effed5c54441570ba6c20b
+size 2236957537

runs/Jul29_19-00-26_c9394c8a1e59/events.out.tfevents.1690657232.c9394c8a1e59.1867.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccde356523f22f9d5221c4da10e2c0bdb779e6da72ca40062b633f7e7b04e3b9
+size 4390

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130408a36f103656122cfc513371d7b28a874cfe136eb527bbc2c0227ef65434
+size 4027